From d5ba623882c3ee1c4cf9dd3bb58ca5db887de9ce Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mateusz=20S=C5=82uszniak?= <mateusz.sluszniak@swmansion.com>
Date: Thu, 22 Oct 2026 16:23:43 +0200
Subject: [PATCH 1/6] feat(nlp): add Opus-MT translation task

---
 apps/nlp/app/_layout.tsx                      |   7 +
 apps/nlp/app/index.tsx                        |   3 +
 apps/nlp/app/translation/index.tsx            | 248 +++++++++++++++++
 .../natural-language/07-translation.md        | 110 ++++++++
 .../08-native-libraries.md                    |  11 +-
 .../api/__snapshots__/apiSurface.test.ts.snap |   4 +
 .../__tests__/api/modelVariants.test.ts       |   1 +
 .../__tests__/tasks/marianTranslation.test.ts | 191 ++++++++++++++
 .../scripts/download-libs.js                  |   4 +-
 .../src/extensions/nlp/index.ts               |   5 +-
 .../extensions/nlp/tasks/marianTranslation.ts | 249 ++++++++++++++++++
 .../extensions/nlp/utils/translationUtils.ts  |  42 +++
 .../src/hooks/useTranslator.ts                |  65 +++++
 packages/react-native-executorch/src/index.ts |   2 +
 .../react-native-executorch/src/models.ts     |  68 +++++
 15 files changed, 1002 insertions(+), 8 deletions(-)
 create mode 100644 apps/nlp/app/translation/index.tsx
 create mode 100644 docs/docs/02-extensions/natural-language/07-translation.md
 create mode 100644 packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts
 create mode 100644 packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts
 create mode 100644 packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts
 create mode 100644 packages/react-native-executorch/src/hooks/useTranslator.ts

diff --git a/apps/nlp/app/_layout.tsx b/apps/nlp/app/_layout.tsx
index 7d637faa15..69520828e7 100644
--- a/apps/nlp/app/_layout.tsx
+++ b/apps/nlp/app/_layout.tsx
@@ -48,6 +48,13 @@ export default function Layout() {
           title: 'Privacy Filter',
         }}
       />
+      <Drawer.Screen
+        name="translation/index"
+        options={{
+          drawerLabel: 'Translation',
+          title: 'Translation',
+        }}
+      />
       <Drawer.Screen
         name="llm/index"
         options={{
diff --git a/apps/nlp/app/index.tsx b/apps/nlp/app/index.tsx
index 7531cc1f30..b2e9b96d97 100644
--- a/apps/nlp/app/index.tsx
+++ b/apps/nlp/app/index.tsx
@@ -23,6 +23,9 @@ export default function Home() {
         <TouchableOpacity style={styles.button} onPress={() => router.navigate('privacy-filter/')}>
           <Text style={styles.buttonText}>Privacy Filter</Text>
         </TouchableOpacity>
+        <TouchableOpacity style={styles.button} onPress={() => router.navigate('translation/')}>
+          <Text style={styles.buttonText}>Translation</Text>
+        </TouchableOpacity>
         <TouchableOpacity style={styles.button} onPress={() => router.navigate('llm/')}>
           <Text style={styles.buttonText}>LLM</Text>
         </TouchableOpacity>
diff --git a/apps/nlp/app/translation/index.tsx b/apps/nlp/app/translation/index.tsx
new file mode 100644
index 0000000000..1948ea3009
--- /dev/null
+++ b/apps/nlp/app/translation/index.tsx
@@ -0,0 +1,248 @@
+import React, { useState } from 'react';
+import {
+  View,
+  Text,
+  TextInput,
+  ScrollView,
+  StyleSheet,
+  TouchableOpacity,
+  KeyboardAvoidingView,
+  Platform,
+} from 'react-native';
+import { useTranslator, models, type MarianTranslatorModel } from 'react-native-executorch';
+import ScreenWrapper from '../../components/ScreenWrapper';
+import { ModelStatus } from '../../components/ModelStatus';
+import { Button } from '../../components/Button';
+import { theme } from '../../theme';
+
+/* cspell:disable */
+const SAMPLES = {
+  en: 'The weather is beautiful today. Shall we go for a walk in the park?\nI will bring something to drink.',
+  de: 'Das Wetter ist heute wunderschön. Sollen wir im Park spazieren gehen?\nIch bringe etwas zu trinken mit.',
+  es: 'Hoy hace un tiempo precioso. ¿Vamos a dar un paseo por el parque?\nYo llevaré algo de beber.',
+  fr: 'Il fait très beau aujourd’hui. On va se promener dans le parc ?\nJ’apporterai quelque chose à boire.',
+} as const;
+/* cspell:enable */
+
+const PAIRS: { label: string; value: MarianTranslatorModel }[] = [
+  { label: 'EN → DE', value: models.translation.OPUS_MT_EN_DE.DEFAULT },
+  { label: 'DE → EN', value: models.translation.OPUS_MT_DE_EN.DEFAULT },
+  { label: 'EN → ES', value: models.translation.OPUS_MT_EN_ES.DEFAULT },
+  { label: 'ES → EN', value: models.translation.OPUS_MT_ES_EN.DEFAULT },
+  { label: 'EN → FR', value: models.translation.OPUS_MT_EN_FR.DEFAULT },
+  { label: 'FR → EN', value: models.translation.OPUS_MT_FR_EN.DEFAULT },
+];
+
+const sampleFor = (model: MarianTranslatorModel): string =>
+  SAMPLES[model.sourceLanguage as keyof typeof SAMPLES] ?? '';
+
+function TranslationContent() {
+  const [selected, setSelected] = useState(0);
+  const active = PAIRS[selected]!;
+  const { isReady, downloadProgress, error, translate, translateStop } = useTranslator(
+    active.value
+  );
+
+  const [text, setText] = useState(sampleFor(active.value));
+  const [output, setOutput] = useState('');
+  const [busy, setBusy] = useState(false);
+  const [runError, setRunError] = useState<string | null>(null);
+  const [elapsedMs, setElapsedMs] = useState<number | null>(null);
+
+  const selectPair = (i: number) => {
+    if (i === selected) return;
+    translateStop?.();
+    setSelected(i);
+    setText(sampleFor(PAIRS[i]!.value));
+    setOutput('');
+    setRunError(null);
+    setElapsedMs(null);
+  };
+
+  const run = async () => {
+    if (!translate || !text.trim()) return;
+    setBusy(true);
+    setRunError(null);
+    setOutput('');
+    setElapsedMs(null);
+    try {
+      const startedAt = Date.now();
+      const result = await translate(text, (piece) => setOutput((prev) => prev + piece));
+      setElapsedMs(Date.now() - startedAt);
+      setOutput(result);
+    } catch (e: any) {
+      const msg = e?.message ?? String(e);
+      if (!/disposed/i.test(msg)) setRunError(msg);
+    } finally {
+      setBusy(false);
+    }
+  };
+
+  return (
+    <KeyboardAvoidingView
+      style={styles.flex}
+      behavior={Platform.OS === 'ios' ? 'padding' : undefined}
+    >
+      <ScrollView style={styles.container} contentContainerStyle={styles.content}>
+        <View style={styles.card}>
+          <Text style={styles.cardTitle}>Translation</Text>
+          <Text style={styles.cardDescription}>
+            On-device Opus-MT translation. Each model covers one language pair and translates the
+            text a sentence at a time, streaming the result as it is decoded.
+          </Text>
+
+          <Text style={styles.fieldLabel}>Language pair</Text>
+          <ScrollView
+            horizontal
+            showsHorizontalScrollIndicator={false}
+            contentContainerStyle={styles.chipRow}
+          >
+            {PAIRS.map((pair, i) => (
+              <TouchableOpacity
+                key={pair.label}
+                style={[styles.chip, i === selected && styles.chipActive]}
+                onPress={() => selectPair(i)}
+              >
+                <Text style={[styles.chipText, i === selected && styles.chipTextActive]}>
+                  {pair.label}
+                </Text>
+              </TouchableOpacity>
+            ))}
+          </ScrollView>
+
+          <ModelStatus
+            isReady={isReady}
+            downloadProgress={downloadProgress}
+            error={error ? error.message : null}
+            modelTypeLabel="model"
+          />
+        </View>
+
+        {runError && (
+          <View style={styles.errorContainer}>
+            <Text style={styles.errorText}>{runError}</Text>
+          </View>
+        )}
+
+        <View style={styles.card}>
+          <Text style={styles.sectionTitle}>Text to translate</Text>
+          <TextInput
+            style={styles.input}
+            value={text}
+            onChangeText={setText}
+            placeholder="Type or paste text…"
+            placeholderTextColor="#999"
+            multiline
+          />
+          <View style={styles.buttonRow}>
+            <Button
+              title="Translate"
+              onPress={run}
+              disabled={!isReady || !translate || !text.trim()}
+              loading={busy}
+            />
+            <Button
+              title="Stop"
+              variant="secondary"
+              onPress={() => translateStop?.()}
+              disabled={!busy}
+            />
+          </View>
+          {elapsedMs !== null && <Text style={styles.statsText}>Time: {elapsedMs} ms</Text>}
+        </View>
+
+        {output !== '' && (
+          <View style={styles.card}>
+            <Text style={styles.sectionTitle}>Translation</Text>
+            <Text style={styles.outputText}>{output}</Text>
+          </View>
+        )}
+      </ScrollView>
+    </KeyboardAvoidingView>
+  );
+}
+
+export default function TranslationScreen() {
+  return (
+    <ScreenWrapper>
+      <TranslationContent />
+    </ScreenWrapper>
+  );
+}
+
+const styles = StyleSheet.create({
+  flex: { flex: 1 },
+  container: { flex: 1, backgroundColor: theme.colors.background },
+  content: { padding: theme.spacing.large, paddingBottom: 40 },
+  card: {
+    backgroundColor: theme.colors.cardBackground,
+    borderRadius: theme.radius.large,
+    padding: 20,
+    marginBottom: 20,
+    borderWidth: 1,
+    borderColor: theme.colors.lightBorder,
+  },
+  cardTitle: {
+    fontSize: theme.typography.title.fontSize,
+    fontWeight: theme.typography.title.fontWeight,
+    color: theme.colors.strongPrimary,
+    marginBottom: 8,
+  },
+  cardDescription: {
+    fontSize: 14,
+    color: theme.colors.textMuted,
+    lineHeight: 20,
+    marginBottom: 16,
+  },
+  fieldLabel: {
+    fontSize: 12,
+    fontWeight: '600',
+    color: theme.colors.textPlaceholder,
+    textTransform: 'uppercase',
+    letterSpacing: 0.5,
+    marginBottom: 8,
+  },
+  chipRow: { gap: 8, paddingBottom: 4, marginBottom: 12 },
+  chip: {
+    paddingHorizontal: 14,
+    paddingVertical: 8,
+    borderRadius: 20,
+    backgroundColor: '#f1f3f5',
+    borderWidth: 1,
+    borderColor: theme.colors.lightBorder,
+  },
+  chipActive: {
+    backgroundColor: theme.colors.strongPrimary,
+    borderColor: theme.colors.strongPrimary,
+  },
+  chipText: { fontSize: 13, fontWeight: '600', color: theme.colors.textMuted },
+  chipTextActive: { color: '#fff' },
+  sectionTitle: { fontSize: 16, fontWeight: '700', color: '#212529', marginBottom: 12 },
+  input: {
+    backgroundColor: '#f1f3f5',
+    borderRadius: theme.radius.small,
+    padding: 12,
+    fontSize: 14,
+    color: '#212529',
+    marginBottom: 16,
+    minHeight: 140,
+    textAlignVertical: 'top',
+    borderWidth: 1,
+    borderColor: theme.colors.lightBorder,
+  },
+  buttonRow: { flexDirection: 'row', gap: theme.spacing.small },
+  statsText: {
+    fontSize: 13,
+    color: theme.colors.textPlaceholder,
+    marginTop: 12,
+    textAlign: 'center',
+  },
+  errorContainer: {
+    backgroundColor: theme.colors.errorBackground,
+    padding: 12,
+    borderRadius: theme.radius.small,
+    marginBottom: 20,
+  },
+  errorText: { color: theme.colors.errorText, fontSize: 14, textAlign: 'center' },
+  outputText: { fontSize: 15, lineHeight: 22, color: '#212529' },
+});
diff --git a/docs/docs/02-extensions/natural-language/07-translation.md b/docs/docs/02-extensions/natural-language/07-translation.md
new file mode 100644
index 0000000000..f044fd9b69
--- /dev/null
+++ b/docs/docs/02-extensions/natural-language/07-translation.md
@@ -0,0 +1,110 @@
+---
+title: Translation
+slug: /extensions/translation
+description: 'Translate text between languages fully on-device in React Native with Opus-MT models.'
+keywords: [react native, translation, machine translation, opus-mt, marian, mobile ml, on-device ai]
+---
+
+# Translation
+
+Translation models turn text in one language into another without sending it off the device. Each [Opus-MT](https://github.com/Helsinki-NLP/Opus-MT) model translates one fixed language pair, such as English to German.
+
+## Quick Start
+
+The [`useTranslator`](../../06-api-reference/functions/useTranslator.md) hook downloads the `.pte` model and tokenizer, loads the pipeline, and manages its lifecycle:
+
+```tsx
+import { models, useTranslator } from 'react-native-executorch';
+
+function MyComponent() {
+  const translator = useTranslator(models.translation.OPUS_MT_EN_DE.DEFAULT);
+
+  // Hook state:
+  // translator.isReady          — true once model and tokenizer are loaded
+  // translator.downloadProgress — 0 to 100 download progress
+  // translator.error            — Error instance if download or load failed
+
+  const handleTranslate = async (text: string) => {
+    if (!translator.isReady || !translator.translate) return;
+
+    const german = await translator.translate(text);
+    console.log(german);
+  };
+}
+```
+
+## Streaming
+
+Pass a callback to receive the translation as it is decoded. Each call gets the newly decoded piece of text; joined together, the pieces equal the returned translation.
+
+```typescript
+let partial = '';
+const result = await translator.translate('How are you? I am fine.', (piece) => {
+  partial += piece;
+  setText(partial);
+});
+```
+
+Call [`translateStop()`](../../06-api-reference/type-aliases/MarianTranslator.md#translatestop) to cancel; [`translate()`](../../06-api-reference/type-aliases/MarianTranslator.md#translate) then resolves with the text translated so far.
+
+## How Input Is Processed
+
+Opus-MT models are trained on single sentences, so the input is split after sentence-ending punctuation (`.`, `!`, `?`) and at line breaks, and each sentence is translated on its own. Line breaks are kept in the output. A single sentence longer than the model's maximum source length (256 tokens) is truncated, and one sentence translates to at most 256 tokens.
+
+## Imperative API
+
+For use outside React components, create the pipeline with [`createMarianTranslator`](../../06-api-reference/functions/createMarianTranslator.md):
+
+```typescript
+import { createMarianTranslator, download, models } from 'react-native-executorch';
+
+const model = await download(models.translation.OPUS_MT_EN_FR.DEFAULT);
+const translator = await createMarianTranslator(model);
+
+try {
+  console.log(await translator.translate('The weather is nice today.'));
+} finally {
+  translator.dispose();
+}
+```
+
+[`translateWorklet`](../../06-api-reference/type-aliases/MarianTranslator.md#translateworklet) runs the same pipeline synchronously on a worklet runtime. See [Worklets & Threading](../../03-core-and-advanced/06-worklets-and-threading.md).
+
+## Available Models
+
+The models are available in [`models.translation`](../../06-api-reference/variables/models.md#translation):
+
+| Model           | Direction         | Size   | Supported Backends |
+| :-------------- | :---------------- | :----- | :----------------- |
+| `OPUS_MT_EN_DE` | English → German  | 107 MB | XNNPACK (CPU)      |
+| `OPUS_MT_DE_EN` | German → English  | 107 MB | XNNPACK (CPU)      |
+| `OPUS_MT_EN_ES` | English → Spanish | 114 MB | XNNPACK (CPU)      |
+| `OPUS_MT_ES_EN` | Spanish → English | 114 MB | XNNPACK (CPU)      |
+| `OPUS_MT_EN_FR` | English → French  | 108 MB | XNNPACK (CPU)      |
+| `OPUS_MT_FR_EN` | French → English  | 108 MB | XNNPACK (CPU)      |
+
+:::info License
+`OPUS_MT_EN_DE` is licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/) and requires attribution to the [Helsinki-NLP Opus-MT](https://huggingface.co/Helsinki-NLP/opus-mt-en-de) project. The other pairs are Apache-2.0.
+:::
+
+## API Reference
+
+### Hooks & Pipelines
+
+- [`useTranslator()`](../../06-api-reference/functions/useTranslator.md) — React hook for translation model downloading, state, and lifecycle.
+- [`createMarianTranslator()`](../../06-api-reference/functions/createMarianTranslator.md) — Imperative factory for Opus-MT translation pipelines.
+
+### Types
+
+- [`MarianTranslator`](../../06-api-reference/type-aliases/MarianTranslator.md) — Translator runner interface ([`translate`](../../06-api-reference/type-aliases/MarianTranslator.md#translate), [`translateWorklet`](../../06-api-reference/type-aliases/MarianTranslator.md#translateworklet), [`translateStop`](../../06-api-reference/type-aliases/MarianTranslator.md#translatestop)).
+- [`MarianTranslatorModel`](../../06-api-reference/type-aliases/MarianTranslatorModel.md) — Model configuration with model path, tokenizer path, and language pair.
+
+### Model Presets
+
+- [`models.translation`](../../06-api-reference/variables/models.md#translation) — Pre-configured translation models registry.
+
+:::info Source Code
+View the implementation on GitHub:
+
+- [`src/extensions/nlp/tasks/marianTranslation.ts` ↗](https://github.com/software-mansion/react-native-executorch/blob/main/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts)
+  :::
diff --git a/docs/docs/03-core-and-advanced/08-native-libraries.md b/docs/docs/03-core-and-advanced/08-native-libraries.md
index 74fc42bb54..0aed2243dc 100644
--- a/docs/docs/03-core-and-advanced/08-native-libraries.md
+++ b/docs/docs/03-core-and-advanced/08-native-libraries.md
@@ -39,11 +39,11 @@ Add a `react-native-executorch` block to your `package.json`:
 
 ### Options
 
-| Option     | Purpose                                                                              | Accepted values                                                                                                                                                                                                                                                                                                                                                           |
-| ---------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `features` | High-level tasks — each automatically expands to the backends and libraries it needs | `"classification"`, `"imageEmbeddings"`, `"inpainting"`, `"instanceSegmentation"`, `"keypointDetection"`, `"llm"`, `"multimodalLLM"`, `"objectDetection"`, `"ocr"`, `"privacyFilter"`, `"segmentAnything"`, `"semanticSegmentation"`, `"speechToText"`, `"styleTransfer"`, `"textEmbeddings"`, `"textToImage"`, `"textToSpeech"`, `"tokenizer"`, `"vad"`, `"verticalOCR"` |
-| `backends` | Hardware acceleration backends directly                                              | `"xnnpack"`, `"coreml"`, `"mlx"`, `"vulkan"`                                                                                                                                                                                                                                                                                                                              |
-| `libs`     | Extra native C++ libraries                                                           | `"opencv"`, `"phonemis"`                                                                                                                                                                                                                                                                                                                                                  |
+| Option     | Purpose                                                                              | Accepted values                                                                                                                                                                                                                                                                                                                                                                            |
+| ---------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `features` | High-level tasks — each automatically expands to the backends and libraries it needs | `"classification"`, `"imageEmbeddings"`, `"inpainting"`, `"instanceSegmentation"`, `"keypointDetection"`, `"llm"`, `"multimodalLLM"`, `"objectDetection"`, `"ocr"`, `"privacyFilter"`, `"segmentAnything"`, `"semanticSegmentation"`, `"speechToText"`, `"styleTransfer"`, `"textEmbeddings"`, `"textToImage"`, `"textToSpeech"`, `"tokenizer"`, `"translation"`, `"vad"`, `"verticalOCR"` |
+| `backends` | Hardware acceleration backends directly                                              | `"xnnpack"`, `"coreml"`, `"mlx"`, `"vulkan"`                                                                                                                                                                                                                                                                                                                                               |
+| `libs`     | Extra native C++ libraries                                                           | `"opencv"`, `"phonemis"`                                                                                                                                                                                                                                                                                                                                                                   |
 
 The three lists are merged, so you can pair high-level `features` with specific `backends` or `libs`. Re-run your package manager install after editing.
 
@@ -90,6 +90,7 @@ Specifying a task under `features` is shorthand: it automatically expands to the
 | `speechToText`         | xnnpack, coreml, mlx, vulkan | —                   |
 | `textToSpeech`         | xnnpack, coreml, mlx, vulkan | phonemis            |
 | `vad`                  | xnnpack                      | —                   |
+| `translation`          | xnnpack                      | —                   |
 | `textEmbeddings`       | xnnpack, coreml, mlx, vulkan | —                   |
 | `imageEmbeddings`      | xnnpack, coreml, mlx, vulkan | opencv              |
 | `classification`       | xnnpack, coreml              | opencv              |
diff --git a/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap b/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap
index 90884cd0ba..eeb42ce0de 100644
--- a/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap
+++ b/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap
@@ -22,6 +22,7 @@ exports[`public API surface exports one hook per user-facing task 1`] = `
   "useTextToImage",
   "useTextToSpeech",
   "useTokenizer",
+  "useTranslator",
   "useVoiceActivityDetector",
 ]
 `;
@@ -76,6 +77,7 @@ exports[`public API surface matches the recorded contents of each namespace 1`]
     "labelEntityType",
     "loadTokenizer",
     "piiSegments",
+    "splitSentences",
     "viterbiDecode",
   ],
   "schema": [
@@ -145,6 +147,7 @@ exports[`public API surface matches the recorded export list 1`] = `
   "createKeypointDetector",
   "createKokoroTextToSpeech",
   "createLLMChatSession",
+  "createMarianTranslator",
   "createObjectDetector",
   "createPaddleOcr",
   "createPrivacyFilter",
@@ -193,6 +196,7 @@ exports[`public API surface matches the recorded export list 1`] = `
   "useTextToImage",
   "useTextToSpeech",
   "useTokenizer",
+  "useTranslator",
   "useVoiceActivityDetector",
   "wrapAsync",
 ]
diff --git a/packages/react-native-executorch/__tests__/api/modelVariants.test.ts b/packages/react-native-executorch/__tests__/api/modelVariants.test.ts
index cb6eef3dc1..b164468f8f 100644
--- a/packages/react-native-executorch/__tests__/api/modelVariants.test.ts
+++ b/packages/react-native-executorch/__tests__/api/modelVariants.test.ts
@@ -427,6 +427,7 @@ describe('feature map', () => {
     textEmbeddings: 'textEmbeddings',
     colbertEmbeddings: 'textEmbeddings',
     privacyFilter: 'privacyFilter',
+    translation: 'translation',
     imageEmbeddings: 'imageEmbeddings',
     textToImage: 'textToImage',
     inpainting: 'inpainting',
diff --git a/packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts b/packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts
new file mode 100644
index 0000000000..9969117de3
--- /dev/null
+++ b/packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts
@@ -0,0 +1,191 @@
+import { RangeDim, constraint, f32, i64, method } from '../../src/core/schema';
+import type { ConcreteDim } from '../../src/core/schema';
+import { createMarianTranslator } from '../../src/extensions/nlp/tasks/marianTranslation';
+import { splitSentences } from '../../src/extensions/nlp/utils/translationUtils';
+import { fakeJsi } from '../support/fakeJsi';
+import { tracked } from '../support/lifetime';
+import type { FakeTensor } from '../support/fakeTensor';
+import { exported } from '../support/fixtures';
+
+const MODEL_PATH = '/models/opus_mt.pte';
+const TOKENIZER_PATH = '/models/tokenizer.json';
+
+const VOCAB = ['<pad>', '</s>', 'hello', 'world', 'hallo', 'welt'];
+const [PAD, EOS, HALLO, WELT] = [0, 1, 4, 5];
+const NUM_CROSS_KV = 12;
+
+const config = {
+  name: 'marian' as const,
+  modelPath: MODEL_PATH,
+  tokenizerPath: TOKENIZER_PATH,
+  sourceLanguage: 'en',
+  targetLanguage: 'de',
+};
+
+/** Builds the exported Opus-MT schema over a source-length domain. */
+function marianSchema(source: ConcreteDim) {
+  const kv = Array(NUM_CROSS_KV).fill(f32(2, source, 4));
+  const kvIndices = [...Array(NUM_CROSS_KV).keys()];
+  const dim = (paramSide: 'input' | 'output', tensorIdx: number) =>
+    ({ paramSide, tensorIdx, dimIdx: 1 }) as const;
+  return exported({
+    ...method('encode', [i64(1, source), i64(1, source)], kv, [
+      constraint.equality(dim('input', 0), dim('input', 1)),
+      ...kvIndices.map((i) => constraint.equality(dim('input', 0), dim('output', i))),
+    ]),
+    ...method(
+      'decode',
+      [i64(1, 1), i64(1), i64(1, source), ...kv],
+      [f32(1, 1, VOCAB.length)],
+      kvIndices.map((i) => constraint.equality(dim('input', 2), dim('input', 3 + i)))
+    ),
+  });
+}
+
+const read = (t: FakeTensor) => Array.from({ length: t.numel }, (_, i) => t.getElement(i));
+
+/** What each `encode` received, and the decoder inputs of each step. */
+const encoded: { ids: number[]; mask: number[] }[] = [];
+const decoded: { token: number; position: number }[] = [];
+
+/**
+ * Registers a model whose decoder emits `target` (then `</s>`) for every
+ * sentence, one token per position.
+ */
+function register(source: ConcreteDim, target: readonly number[] = [HALLO, WELT]) {
+  encoded.length = 0;
+  decoded.length = 0;
+  fakeJsi.registerModel(MODEL_PATH, {
+    schema: marianSchema(source),
+    execute: (methodName, inputs, outputs) => {
+      if (methodName === 'encode') {
+        const [ids, mask] = inputs as [FakeTensor, FakeTensor];
+        encoded.push({ ids: read(ids), mask: read(mask) });
+        return;
+      }
+      const [token, position] = inputs as [FakeTensor, FakeTensor];
+      const pos = position.getElement(0);
+      decoded.push({ token: token.getElement(0), position: pos });
+      const logits = outputs[0]!;
+      for (let i = 0; i < logits.numel; i++) logits.setElement(i, 0);
+      logits.setElement(target[pos] ?? EOS, 1);
+    },
+  });
+  fakeJsi.registerTokenizer(TOKENIZER_PATH, { tokens: VOCAB, specialIds: [PAD, EOS] });
+}
+
+describe('createMarianTranslator', () => {
+  it('encodes the source with </s> and decodes greedily from <pad> until </s>', async () => {
+    register(RangeDim(1, 8));
+    const translator = tracked(await createMarianTranslator(config));
+
+    expect(await translator.translate('hello world')).toBe('hallo welt');
+    expect(encoded).toEqual([{ ids: [2, 3, EOS], mask: [1, 1, 1] }]);
+    expect(decoded).toEqual([
+      { token: PAD, position: 0 },
+      { token: HALLO, position: 1 },
+      { token: WELT, position: 2 },
+    ]);
+  });
+
+  it('does not append a second </s> when the tokenizer already adds one', async () => {
+    register(RangeDim(1, 8));
+    fakeJsi.registerTokenizer(TOKENIZER_PATH, { tokens: VOCAB, suffix: [EOS] });
+    const translator = tracked(await createMarianTranslator(config));
+
+    await translator.translate('hello world');
+    expect(encoded[0]!.ids).toEqual([2, 3, EOS]);
+  });
+
+  it('pads and masks the source when the export fixes its length', async () => {
+    register(RangeDim(6, 6));
+    const translator = tracked(await createMarianTranslator(config));
+
+    expect(await translator.translate('hello world')).toBe('hallo welt');
+    expect(encoded).toEqual([{ ids: [2, 3, EOS, PAD, PAD, PAD], mask: [1, 1, 1, 0, 0, 0] }]);
+  });
+
+  it('truncates a long sentence to the maximum source length, ending in </s>', async () => {
+    register(RangeDim(1, 4));
+    const translator = tracked(await createMarianTranslator(config));
+
+    await translator.translate('hello world hello world hello');
+    expect(encoded[0]!.ids).toEqual([2, 3, 2, EOS]);
+  });
+
+  it('translates sentence by sentence and keeps line breaks', async () => {
+    register(RangeDim(1, 8));
+    const translator = tracked(await createMarianTranslator(config));
+
+    const text = await translator.translate('hello. world!\n\nhello');
+    expect(text).toBe('hallo welt hallo welt\n\nhallo welt');
+    expect(encoded).toHaveLength(3);
+  });
+
+  it('streams pieces that add up to the translation', async () => {
+    register(RangeDim(1, 8));
+    const translator = tracked(await createMarianTranslator(config));
+    const pieces: string[] = [];
+
+    const text = await translator.translate('hello world', (piece) => pieces.push(piece));
+    // Pieces are delivered on the RN thread, which the mock defers to a macrotask.
+    await new Promise((resolve) => setTimeout(resolve, 0));
+    expect(pieces.join('')).toBe(text);
+    expect(pieces.length).toBeGreaterThan(1);
+  });
+
+  it('stops when the decoder fills its cache without emitting </s>', async () => {
+    register(RangeDim(1, 8), Array(300).fill(HALLO));
+    const translator = tracked(await createMarianTranslator(config));
+
+    await translator.translate('hello');
+    expect(decoded).toHaveLength(256);
+  });
+
+  it('rejects a model without the source-length constraints', async () => {
+    const kv = Array(NUM_CROSS_KV).fill(f32(2, RangeDim(1, 8), 4));
+    fakeJsi.registerModel(MODEL_PATH, {
+      schema: exported({
+        ...method('encode', [i64(1, RangeDim(1, 8)), i64(1, RangeDim(1, 8))], kv),
+        ...method(
+          'decode',
+          [i64(1, 1), i64(1), i64(1, RangeDim(1, 8)), ...kv],
+          [f32(1, 1, VOCAB.length)]
+        ),
+      }),
+    });
+    fakeJsi.registerTokenizer(TOKENIZER_PATH, { tokens: VOCAB });
+
+    await expect(createMarianTranslator(config)).rejects.toThrow(
+      /doesn't match any of the provided variants/
+    );
+  });
+
+  it('releases everything on dispose', async () => {
+    register(RangeDim(1, 8));
+    const translator = tracked(await createMarianTranslator(config));
+    await translator.translate('hello world. hello');
+    translator.dispose();
+
+    expect(fakeJsi.liveTensors()).toBe(0);
+    expect(fakeJsi.liveModels()).toEqual([]);
+    expect(fakeJsi.liveTokenizers()).toEqual([]);
+  });
+});
+
+describe('splitSentences', () => {
+  it('splits after closing punctuation and keeps line breaks as separators', () => {
+    expect(splitSentences('Hi there. How are you?\nFine!')).toEqual([
+      { sentence: 'Hi there.', separator: ' ' },
+      { sentence: 'How are you?', separator: '\n' },
+      { sentence: 'Fine!', separator: '' },
+    ]);
+  });
+
+  it('keeps closing quotes with their sentence and does not split decimals', () => {
+    expect(splitSentences('He said "go." It costs 3.50 now')).toEqual([
+      { sentence: 'He said "go."', separator: ' ' },
+      { sentence: 'It costs 3.50 now', separator: '' },
+    ]);
+  });
+});
diff --git a/packages/react-native-executorch/scripts/download-libs.js b/packages/react-native-executorch/scripts/download-libs.js
index 38b990f29c..4366be922c 100644
--- a/packages/react-native-executorch/scripts/download-libs.js
+++ b/packages/react-native-executorch/scripts/download-libs.js
@@ -42,7 +42,7 @@
  * Recognized values:
  *   backends:  xnnpack, coreml (iOS), mlx (iOS), vulkan (Android)
  *   libs:      opencv, phonemis
- *   features:  llm, multimodalLLM, speechToText, textToSpeech, vad, privacyFilter,
+ *   features:  llm, multimodalLLM, speechToText, textToSpeech, vad, privacyFilter, translation,
  *              textEmbeddings, imageEmbeddings,
  *              classification, objectDetection, depthEstimation, semanticSegmentation, instanceSegmentation,
  *              ocr, verticalOCR, keypointDetection, styleTransfer, textToImage, segmentAnything,
@@ -142,6 +142,8 @@ const FEATURE_MAP = {
   },
   // FSMN VAD — xnnpack only.
   vad: { backends: ['xnnpack'], libs: [] },
+  // Opus-MT ships xnnpack int8 only: it beat Core ML, MLX and Vulkan on device.
+  translation: { backends: ['xnnpack'], libs: [] },
   // The MiniLM/CLIP-text/distiluse family ships coreml alongside xnnpack,
   // LFM2.5-Embedding and distiluse add MLX iOS exports, and every sentence
   // transformer now ships a vulkan Android export.
diff --git a/packages/react-native-executorch/src/extensions/nlp/index.ts b/packages/react-native-executorch/src/extensions/nlp/index.ts
index 476fe02d37..915c861e5e 100644
--- a/packages/react-native-executorch/src/extensions/nlp/index.ts
+++ b/packages/react-native-executorch/src/extensions/nlp/index.ts
@@ -1,7 +1,8 @@
 /**
- * Natural Language Processing (NLP) tokenization, text embedding, and privacy
- * filtering pipelines.
+ * Natural Language Processing (NLP) tokenization, text embedding, privacy
+ * filtering, and translation pipelines.
  */
 
 export * from './tokenizer';
 export * from './utils/privacyFilterUtils';
+export * from './utils/translationUtils';
diff --git a/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts b/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts
new file mode 100644
index 0000000000..4ebcd24113
--- /dev/null
+++ b/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts
@@ -0,0 +1,249 @@
+/**
+ * Marian (Opus-MT) machine translation task pipeline.
+ */
+
+import type { WorkletRuntime } from 'react-native-worklets';
+import { scheduleOnRN, createSynchronizable } from 'react-native-worklets';
+
+import { tensor, type Tensor } from '../../../core/tensor';
+import { loadModel } from '../../../core/model';
+import { wrapAsync } from '../../../core/runtime';
+import {
+  constraint,
+  f32,
+  i64,
+  method,
+  validateSpec,
+  DynamicDim as Dyn,
+} from '../../../core/schema';
+import { createResourceScope } from '../../../core/lifetime';
+
+import { argmax } from '../../math';
+import { loadTokenizer } from '../tokenizer';
+import { splitSentences } from '../utils/translationUtils';
+
+// Positions in the decoder's self-attention KV cache, i.e. the most tokens one
+// sentence can translate to.
+const MAX_TARGET_LEN = 256;
+// One cross-attention key and value per decoder layer (Opus-MT has 6).
+const NUM_CROSS_KV = 12;
+
+/**
+ * Paths and metadata required to instantiate a Marian (Opus-MT) translator.
+ * Each model translates one fixed language pair.
+ * @category NLP / Types
+ */
+export type MarianTranslatorModel = {
+  /** Identifies the pipeline this config belongs to. */
+  readonly name: 'marian';
+  /** Local path or remote URL of the `.pte` model file. */
+  readonly modelPath: string;
+  /** Local path or remote URL of the tokenizer file. */
+  readonly tokenizerPath: string;
+  /** ISO 639-1 code of the language the model translates from. */
+  readonly sourceLanguage: string;
+  /** ISO 639-1 code of the language the model translates to. */
+  readonly targetLanguage: string;
+};
+
+/**
+ * Marian (Opus-MT) translation task runner.
+ * @category NLP / Types
+ */
+export type MarianTranslator = {
+  /**
+   * Releases all allocated native resources.
+   */
+  readonly dispose: () => void;
+
+  /**
+   * Asynchronously translates text from the model's source language to its
+   * target language. The text is split into sentences, which are translated
+   * one at a time; line breaks are kept.
+   * @param text The text to translate.
+   * @param onToken Optional callback fired on the RN thread with each newly
+   * decoded piece of the translation.
+   * @returns A promise resolving to the translated text.
+   * @throws {RnExecuTorchError} With code `RESOURCE_BUSY` if the model is in
+   * use, or `RESOURCE_DISPOSED` if disposed.
+   */
+  readonly translate: (text: string, onToken?: (token: string) => void) => Promise<string>;
+
+  /**
+   * Synchronous version of {@link translate} to be executed directly on the
+   * caller or worklet thread.
+   */
+  readonly translateWorklet: (text: string, onToken?: (token: string) => void) => string;
+
+  /**
+   * Interrupts an active translation call, which returns the text translated
+   * so far.
+   */
+  readonly translateStop: () => void;
+};
+
+/**
+ * Creates a translator for Marian encoder-decoder models such as Opus-MT.
+ *
+ * The source sentence is encoded once into per-layer cross-attention keys and
+ * values, then decoded greedily one token at a time, starting from the pad
+ * token, until the end-of-sentence token. Sentences longer than the model's
+ * maximum source length are truncated.
+ * @category NLP / Tasks
+ * @param config Model and tokenizer paths. See {@link MarianTranslatorModel}.
+ * @param runtime Optional worklet runtime thread on which to run the model
+ * execution.
+ * @returns A promise resolving to the instantiated {@link MarianTranslator}.
+ * @throws {RnExecuTorchError} With code `LOAD_FAILED` if the model or
+ * tokenizer fails to load, or `SCHEMA_MISMATCH` if the model schema does not
+ * match the Marian specification.
+ */
+export async function createMarianTranslator(
+  config: MarianTranslatorModel,
+  runtime?: WorkletRuntime
+): Promise<MarianTranslator> {
+  const scope = createResourceScope();
+  const dispose = scope.dispose;
+
+  try {
+    const { modelPath, tokenizerPath } = config;
+    const model = scope.track(await wrapAsync(loadModel, runtime)(modelPath));
+    const tokenizer = scope.track(await wrapAsync(loadTokenizer, runtime)(tokenizerPath));
+
+    // The source length S must agree across the ids, the mask and every
+    // cross-attention key and value.
+    const crossKv = Array(NUM_CROSS_KV).fill(f32('H', Dyn('S'), 'Dh'));
+    const kvIndices = [...Array(NUM_CROSS_KV).keys()];
+    const sourceDim = (paramSide: 'input' | 'output', tensorIdx: number) =>
+      ({ paramSide, tensorIdx, dimIdx: 1 }) as const;
+    const { dims } = validateSpec(model.schema, {
+      default: {
+        ...method('encode', [i64(1, Dyn('S')), i64(1, Dyn('S'))], crossKv, [
+          constraint.equality(sourceDim('input', 0), sourceDim('input', 1)),
+          ...kvIndices.map((i) =>
+            constraint.equality(sourceDim('input', 0), sourceDim('output', i))
+          ),
+        ]),
+        ...method(
+          'decode',
+          [i64(1, 1), i64(1), i64(1, Dyn('S')), ...crossKv],
+          [f32(1, 1, 'V')],
+          kvIndices.map((i) =>
+            constraint.equality(sourceDim('input', 2), sourceDim('input', 3 + i))
+          )
+        ),
+      },
+    });
+
+    const [sourceLen] = dims.range('S');
+    const [numHeads, headDim, vocabSize] = dims.constant('H', 'Dh', 'V');
+    // Core ML exports a fixed source length; shorter inputs are padded and
+    // masked.
+    const isPadded = sourceLen.min === sourceLen.max;
+
+    const padToken = tokenizer.tokenToId('<pad>');
+    const eosToken = tokenizer.tokenToId('</s>');
+
+    const tensors = [
+      tensor('int64', [1, 1]), // tToken
+      tensor('int64', [1]), // tPosition
+      tensor('float32', [1, 1, vocabSize]), // tLogits
+      tensor('int32', [1, 1, 1]), // tArgmax
+    ] as const;
+    tensors.forEach(scope.track);
+    const [tToken, tPosition, tLogits, tArgmax] = tensors;
+
+    // Encoder inputs and outputs depend on the source length, so they are
+    // allocated per sentence unless that length is fixed.
+    const allocateSource = (len: number): Tensor[] => {
+      'worklet';
+      return [
+        tensor('int64', [1, len]), // tSourceIds
+        tensor('int64', [1, len]), // tSourceMask
+        ...Array.from({ length: NUM_CROSS_KV }, () => tensor('float32', [numHeads, len, headDim])),
+      ];
+    };
+    const paddedSource = isPadded ? allocateSource(sourceLen.max) : [];
+    paddedSource.forEach(scope.track);
+
+    const isCancelled = createSynchronizable(false);
+
+    const translateSentence = (text: string, onText: (text: string) => void): string => {
+      'worklet';
+      const ids = Array.from(tokenizer.encode(text));
+      if (ids[ids.length - 1] !== eosToken) ids.push(eosToken);
+      if (ids.length > sourceLen.max) {
+        ids.length = sourceLen.max;
+        ids[ids.length - 1] = eosToken;
+      }
+
+      const len = isPadded ? sourceLen.max : ids.length;
+      const idsData = new BigInt64Array(len).fill(BigInt(padToken));
+      const maskData = new BigInt64Array(len);
+      ids.forEach((id, i) => {
+        idsData[i] = BigInt(id);
+        maskData[i] = 1n;
+      });
+
+      const source = isPadded ? paddedSource : allocateSource(len);
+      try {
+        const [tSourceIds, tSourceMask, ...tCrossKv] = source as [Tensor, Tensor, ...Tensor[]];
+        tSourceIds.setData(idsData);
+        tSourceMask.setData(maskData);
+        model.execute('encode', [tSourceIds, tSourceMask], tCrossKv);
+
+        const generated: number[] = [];
+        let decoded = '';
+        let token = padToken;
+        for (let position = 0; position < MAX_TARGET_LEN; position++) {
+          if (isCancelled.getBlocking()) break;
+
+          tToken.setData(BigInt64Array.of(BigInt(token)));
+          tPosition.setData(BigInt64Array.of(BigInt(position)));
+          model.execute('decode', [tToken, tPosition, tSourceMask, ...tCrossKv], [tLogits]);
+          token = tLogits.through(argmax, tArgmax).getData(new Int32Array(1))[0]!;
+          if (token === eosToken) break;
+
+          generated.push(token);
+          // SentencePiece spacing depends on the following piece, so stream
+          // the growth of the whole decoded text instead of single pieces.
+          const next = tokenizer.decode(Int32Array.from(generated));
+          if (next.startsWith(decoded) && next.length > decoded.length) {
+            onText(next.slice(decoded.length));
+          }
+          decoded = next;
+        }
+        return decoded;
+      } finally {
+        if (!isPadded) source.forEach((t) => t.dispose());
+      }
+    };
+
+    const translateWorklet = (text: string, onToken?: (token: string) => void): string => {
+      'worklet';
+      isCancelled.setBlocking(false);
+
+      const emit = (piece: string) => {
+        'worklet';
+        if (onToken && piece !== '') scheduleOnRN(onToken, piece);
+      };
+
+      let result = '';
+      for (const { sentence, separator } of splitSentences(text)) {
+        if (isCancelled.getBlocking()) break;
+        if (sentence.trim() !== '') result += translateSentence(sentence, emit);
+        emit(separator);
+        result += separator;
+      }
+      return result.trim();
+    };
+
+    const translate = wrapAsync(translateWorklet, runtime);
+    const translateStop = () => isCancelled.setBlocking(true);
+
+    return { dispose, translate, translateWorklet, translateStop };
+  } catch (error) {
+    dispose();
+    throw error;
+  }
+}
diff --git a/packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts b/packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts
new file mode 100644
index 0000000000..e5909a8c08
--- /dev/null
+++ b/packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts
@@ -0,0 +1,42 @@
+/**
+ * Text segmentation shared by the translation pipelines.
+ */
+
+/**
+ * A sentence and the whitespace that followed it in the source text.
+ * @category NLP / Types
+ */
+export type SentenceSegment = {
+  /** The sentence, including its closing punctuation. */
+  readonly sentence: string;
+  /** The line breaks that followed it, or a single space if there were none. */
+  readonly separator: string;
+};
+
+/**
+ * Splits text into sentences for sentence-level translation models. Line
+ * breaks are kept as separators so the translation keeps the source layout.
+ * @category NLP / Functions
+ * @param text The text to split.
+ * @returns The sentences in order, each with the separator that followed it.
+ * The last separator is empty.
+ */
+export function splitSentences(text: string): SentenceSegment[] {
+  'worklet';
+  const segments: SentenceSegment[] = [];
+  // Closing punctuation (optionally followed by closing quotes or brackets) and
+  // the whitespace after it, or a run of line breaks. Built per call: a regex
+  // literal at module scope cannot be captured by a worklet.
+  const boundary = /([.!?…。！？]+["'”’»)\]]*)(\s+)|(\n+)/g;
+  let start = 0;
+  let match: RegExpExecArray | null;
+  while ((match = boundary.exec(text)) !== null) {
+    const end = match.index + (match[1]?.length ?? 0);
+    const whitespace = match[2] ?? match[3]!;
+    const breaks = whitespace.replace(/[^\n]/g, '');
+    segments.push({ sentence: text.slice(start, end), separator: breaks || ' ' });
+    start = match.index + match[0].length;
+  }
+  segments.push({ sentence: text.slice(start), separator: '' });
+  return segments;
+}
diff --git a/packages/react-native-executorch/src/hooks/useTranslator.ts b/packages/react-native-executorch/src/hooks/useTranslator.ts
new file mode 100644
index 0000000000..ae784b299e
--- /dev/null
+++ b/packages/react-native-executorch/src/hooks/useTranslator.ts
@@ -0,0 +1,65 @@
+import { useModel } from './useModel';
+import { useResourceDownload, type ResourceOptions } from './useResourceDownload';
+import {
+  createMarianTranslator,
+  type MarianTranslatorModel,
+  type MarianTranslator,
+} from '../extensions/nlp/tasks/marianTranslation';
+
+/**
+ * React hook to load and run a Marian (Opus-MT) translation pipeline.
+ *
+ * This hook manages downloading (if remote URLs are provided) and loading the
+ * model and tokenizer, tracking download progress and load errors, and
+ * releasing native memory when the component unmounts or the configuration
+ * changes.
+ *
+ * For imperative usage, see {@link createMarianTranslator}.
+ * @category Hooks
+ * @param config The translation model configuration.
+ * See {@link MarianTranslatorModel}.
+ * @param options Load and caching options. See {@link ResourceOptions}.
+ * @returns The same object as {@link MarianTranslator} (without `dispose`),
+ * combined with loading state and download progress.
+ * @see {@link MarianTranslator}
+ */
+export function useTranslator(
+  config: MarianTranslatorModel,
+  options?: ResourceOptions
+): {
+  /** Whether the pipeline is loaded and ready to translate. */
+  isReady: boolean;
+  /** The download or load error, if any. */
+  error: Error | undefined;
+  /** Download progress across every asset, in percent. */
+  downloadProgress: number;
+  /** The config with every remote URL resolved to a local path. */
+  resource: MarianTranslatorModel | undefined;
+  /** Translates text. Undefined until the pipeline is ready. */
+  translate: MarianTranslator['translate'] | undefined;
+  /** Cancels an in-flight translation. Undefined until the pipeline is ready. */
+  translateStop: MarianTranslator['translateStop'] | undefined;
+};
+
+export function useTranslator(config: MarianTranslatorModel, options?: ResourceOptions) {
+  // Each config names the pipeline it belongs to, so the factory is resolved
+  // from that tag alone.
+  const factory = (translatorConfig: MarianTranslatorModel): Promise<MarianTranslator> => {
+    switch (translatorConfig.name) {
+      case 'marian':
+        return createMarianTranslator(translatorConfig);
+    }
+  };
+
+  const { resource, downloadProgress, downloadError } = useResourceDownload(config, options);
+  const { model, error } = useModel(factory, resource);
+
+  return {
+    isReady: !!model,
+    error: downloadError || error,
+    downloadProgress,
+    resource,
+    translate: model?.translate,
+    translateStop: model?.translateStop,
+  };
+}
diff --git a/packages/react-native-executorch/src/index.ts b/packages/react-native-executorch/src/index.ts
index 876061b944..a9a81aff9a 100644
--- a/packages/react-native-executorch/src/index.ts
+++ b/packages/react-native-executorch/src/index.ts
@@ -57,6 +57,7 @@ export * from './hooks/useLLMChatSession';
 export * from './hooks/useTextEmbedder';
 export * from './hooks/useColbertEmbedder';
 export * from './hooks/usePrivacyFilter';
+export * from './hooks/useTranslator';
 export * from './hooks/useImageEmbedder';
 export * from './hooks/useVoiceActivityDetector';
 export * from './hooks/useSpeechToText';
@@ -90,6 +91,7 @@ export * from './extensions/nlp/tasks/tokenization';
 export * from './extensions/nlp/tasks/textEmbedding';
 export * from './extensions/nlp/tasks/colbertEmbedding';
 export * from './extensions/nlp/tasks/privacyFilter';
+export * from './extensions/nlp/tasks/marianTranslation';
 export * from './extensions/speech/tasks/fsmnVoiceActivityDetection';
 export * from './extensions/speech/tasks/whisperSpeechToText';
 export * from './extensions/speech/tasks/supertonicTextToSpeech';
diff --git a/packages/react-native-executorch/src/models.ts b/packages/react-native-executorch/src/models.ts
index ad8074f9a2..50a0ba121d 100644
--- a/packages/react-native-executorch/src/models.ts
+++ b/packages/react-native-executorch/src/models.ts
@@ -30,6 +30,7 @@ import type { SdxsTextToImageModel } from './extensions/cv/tasks/sdxsTextToImage
 import type { TextEmbedderModel } from './extensions/nlp/tasks/textEmbedding';
 import type { ColbertEmbedderModel } from './extensions/nlp/tasks/colbertEmbedding';
 import type { PrivacyFilterModel } from './extensions/nlp/tasks/privacyFilter';
+import type { MarianTranslatorModel } from './extensions/nlp/tasks/marianTranslation';
 import type { FsmnVadModel } from './extensions/speech/tasks/fsmnVoiceActivityDetection';
 import type { SupertonicTtsModel } from './extensions/speech/tasks/supertonicTextToSpeech';
 import type { KokoroTtsModel } from './extensions/speech/tasks/kokoroTextToSpeech';
@@ -2151,6 +2152,54 @@ const PPOCRV6_SMALL_VULKAN_FP16: PaddleOcrModel = {
   modelOpts: PPOCRV6_OPTS,
 };
 
+// =============================================================================
+// Translation
+// =============================================================================
+const OPUS_MT_BASE_URL = `${BASE_URL}/opus-mt-ExecuTorch/${NEXT_VERSION_TAG}`;
+
+const OPUS_MT_EN_DE_XNNPACK_INT8: MarianTranslatorModel = {
+  name: 'marian',
+  modelPath: `${OPUS_MT_BASE_URL}/en_de/xnnpack/opus_mt_en_de_xnnpack_int8.pte`,
+  tokenizerPath: `${OPUS_MT_BASE_URL}/en_de/tokenizer.json`,
+  sourceLanguage: 'en',
+  targetLanguage: 'de',
+};
+const OPUS_MT_DE_EN_XNNPACK_INT8: MarianTranslatorModel = {
+  name: 'marian',
+  modelPath: `${OPUS_MT_BASE_URL}/de_en/xnnpack/opus_mt_de_en_xnnpack_int8.pte`,
+  tokenizerPath: `${OPUS_MT_BASE_URL}/de_en/tokenizer.json`,
+  sourceLanguage: 'de',
+  targetLanguage: 'en',
+};
+const OPUS_MT_EN_ES_XNNPACK_INT8: MarianTranslatorModel = {
+  name: 'marian',
+  modelPath: `${OPUS_MT_BASE_URL}/en_es/xnnpack/opus_mt_en_es_xnnpack_int8.pte`,
+  tokenizerPath: `${OPUS_MT_BASE_URL}/en_es/tokenizer.json`,
+  sourceLanguage: 'en',
+  targetLanguage: 'es',
+};
+const OPUS_MT_ES_EN_XNNPACK_INT8: MarianTranslatorModel = {
+  name: 'marian',
+  modelPath: `${OPUS_MT_BASE_URL}/es_en/xnnpack/opus_mt_es_en_xnnpack_int8.pte`,
+  tokenizerPath: `${OPUS_MT_BASE_URL}/es_en/tokenizer.json`,
+  sourceLanguage: 'es',
+  targetLanguage: 'en',
+};
+const OPUS_MT_EN_FR_XNNPACK_INT8: MarianTranslatorModel = {
+  name: 'marian',
+  modelPath: `${OPUS_MT_BASE_URL}/en_fr/xnnpack/opus_mt_en_fr_xnnpack_int8.pte`,
+  tokenizerPath: `${OPUS_MT_BASE_URL}/en_fr/tokenizer.json`,
+  sourceLanguage: 'en',
+  targetLanguage: 'fr',
+};
+const OPUS_MT_FR_EN_XNNPACK_INT8: MarianTranslatorModel = {
+  name: 'marian',
+  modelPath: `${OPUS_MT_BASE_URL}/fr_en/xnnpack/opus_mt_fr_en_xnnpack_int8.pte`,
+  tokenizerPath: `${OPUS_MT_BASE_URL}/fr_en/tokenizer.json`,
+  sourceLanguage: 'fr',
+  targetLanguage: 'en',
+};
+
 // =============================================================================
 // LLMs
 // =============================================================================
@@ -3719,6 +3768,25 @@ export const models = {
     }),
   },
 
+  /**
+   * Machine translation models. Opus-MT models each translate one language
+   * pair, a sentence at a time.
+   */
+  translation: {
+    /** Opus-MT English to German. */
+    OPUS_MT_EN_DE: variants({ XNNPACK_INT8: OPUS_MT_EN_DE_XNNPACK_INT8 }),
+    /** Opus-MT German to English. */
+    OPUS_MT_DE_EN: variants({ XNNPACK_INT8: OPUS_MT_DE_EN_XNNPACK_INT8 }),
+    /** Opus-MT English to Spanish. */
+    OPUS_MT_EN_ES: variants({ XNNPACK_INT8: OPUS_MT_EN_ES_XNNPACK_INT8 }),
+    /** Opus-MT Spanish to English. */
+    OPUS_MT_ES_EN: variants({ XNNPACK_INT8: OPUS_MT_ES_EN_XNNPACK_INT8 }),
+    /** Opus-MT English to French. */
+    OPUS_MT_EN_FR: variants({ XNNPACK_INT8: OPUS_MT_EN_FR_XNNPACK_INT8 }),
+    /** Opus-MT French to English. */
+    OPUS_MT_FR_EN: variants({ XNNPACK_INT8: OPUS_MT_FR_EN_XNNPACK_INT8 }),
+  },
+
   /**
    * Image feature extraction and vision embedding models.
    */

From cabba97cd5de1f6eee7c98f2a3796b8e1bc16f2a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mateusz=20S=C5=82uszniak?= <mateusz.sluszniak@swmansion.com>
Date: Fri, 23 Oct 2026 12:32:28 +0200
Subject: [PATCH 2/6] feat(nlp): add EuroLLM translation with a per-call
 language pair

---
 apps/nlp/app/translation/index.tsx            | 126 ++++++----
 .../natural-language/07-translation.md        |  82 +++++--
 .../08-native-libraries.md                    |   2 +-
 .../api/__snapshots__/apiSurface.test.ts.snap |   1 +
 .../__tests__/tasks/llmTranslation.test.ts    | 123 ++++++++++
 .../__tests__/tasks/marianTranslation.test.ts |  27 ++-
 .../scripts/download-libs.js                  |   2 +-
 .../extensions/llm/tasks/llmTranslation.ts    | 228 ++++++++++++++++++
 .../extensions/nlp/tasks/marianTranslation.ts |  62 ++---
 .../extensions/nlp/utils/translationUtils.ts  |  48 +++-
 .../src/hooks/useTranslator.ts                |  45 ++--
 packages/react-native-executorch/src/index.ts |   2 +
 .../react-native-executorch/src/models.ts     |  21 ++
 13 files changed, 645 insertions(+), 124 deletions(-)
 create mode 100644 packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts
 create mode 100644 packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts

diff --git a/apps/nlp/app/translation/index.tsx b/apps/nlp/app/translation/index.tsx
index 1948ea3009..ab34530a0a 100644
--- a/apps/nlp/app/translation/index.tsx
+++ b/apps/nlp/app/translation/index.tsx
@@ -9,51 +9,83 @@ import {
   KeyboardAvoidingView,
   Platform,
 } from 'react-native';
-import { useTranslator, models, type MarianTranslatorModel } from 'react-native-executorch';
+import {
+  useTranslator,
+  models,
+  type TranslationLanguages,
+  type TranslatorModel,
+} from 'react-native-executorch';
 import ScreenWrapper from '../../components/ScreenWrapper';
 import { ModelStatus } from '../../components/ModelStatus';
 import { Button } from '../../components/Button';
 import { theme } from '../../theme';
 
 /* cspell:disable */
-const SAMPLES = {
+const SAMPLES: Record<string, string> = {
   en: 'The weather is beautiful today. Shall we go for a walk in the park?\nI will bring something to drink.',
   de: 'Das Wetter ist heute wunderschön. Sollen wir im Park spazieren gehen?\nIch bringe etwas zu trinken mit.',
   es: 'Hoy hace un tiempo precioso. ¿Vamos a dar un paseo por el parque?\nYo llevaré algo de beber.',
   fr: 'Il fait très beau aujourd’hui. On va se promener dans le parc ?\nJ’apporterai quelque chose à boire.',
-} as const;
+  pl: 'Dzisiaj jest piękna pogoda. Może pójdziemy na spacer do parku?\nPrzyniosę coś do picia.',
+};
 /* cspell:enable */
 
-const PAIRS: { label: string; value: MarianTranslatorModel }[] = [
-  { label: 'EN → DE', value: models.translation.OPUS_MT_EN_DE.DEFAULT },
-  { label: 'DE → EN', value: models.translation.OPUS_MT_DE_EN.DEFAULT },
-  { label: 'EN → ES', value: models.translation.OPUS_MT_EN_ES.DEFAULT },
-  { label: 'ES → EN', value: models.translation.OPUS_MT_ES_EN.DEFAULT },
-  { label: 'EN → FR', value: models.translation.OPUS_MT_EN_FR.DEFAULT },
-  { label: 'FR → EN', value: models.translation.OPUS_MT_FR_EN.DEFAULT },
+type Pair = { label: string; languages: TranslationLanguages };
+const pair = (sourceLanguage: string, targetLanguage: string): Pair => ({
+  label: `${sourceLanguage.toUpperCase()} → ${targetLanguage.toUpperCase()}`,
+  languages: { sourceLanguage, targetLanguage },
+});
+
+// Opus-MT ships one model per pair; EuroLLM translates every pair with one.
+const OPUS_MT: { pair: Pair; model: TranslatorModel }[] = [
+  { pair: pair('en', 'de'), model: models.translation.OPUS_MT_EN_DE.DEFAULT },
+  { pair: pair('de', 'en'), model: models.translation.OPUS_MT_DE_EN.DEFAULT },
+  { pair: pair('en', 'es'), model: models.translation.OPUS_MT_EN_ES.DEFAULT },
+  { pair: pair('es', 'en'), model: models.translation.OPUS_MT_ES_EN.DEFAULT },
+  { pair: pair('en', 'fr'), model: models.translation.OPUS_MT_EN_FR.DEFAULT },
+  { pair: pair('fr', 'en'), model: models.translation.OPUS_MT_FR_EN.DEFAULT },
 ];
+const EUROLLM_PAIRS = [...OPUS_MT.map((m) => m.pair), pair('en', 'pl'), pair('pl', 'en')];
 
-const sampleFor = (model: MarianTranslatorModel): string =>
-  SAMPLES[model.sourceLanguage as keyof typeof SAMPLES] ?? '';
+const FAMILIES = [
+  {
+    label: 'Opus-MT',
+    description:
+      'One small model per language pair. Translates a sentence at a time and streams the result as it is decoded.',
+    pairs: OPUS_MT.map((m) => m.pair),
+    modelFor: (i: number) => OPUS_MT[i]!.model,
+  },
+  {
+    label: 'EuroLLM',
+    description:
+      'One 1.7 GB model for 35 languages, so switching the pair does not reload it. Translates a line at a time.',
+    pairs: EUROLLM_PAIRS,
+    modelFor: () => models.translation.EUROLLM_1_7B.DEFAULT as TranslatorModel,
+  },
+];
 
 function TranslationContent() {
+  const [family, setFamily] = useState(0);
   const [selected, setSelected] = useState(0);
-  const active = PAIRS[selected]!;
+  const { pairs, modelFor, description } = FAMILIES[family]!;
+  const active = pairs[selected]!;
   const { isReady, downloadProgress, error, translate, translateStop } = useTranslator(
-    active.value
+    modelFor(selected)
   );
 
-  const [text, setText] = useState(sampleFor(active.value));
+  const [text, setText] = useState(SAMPLES[active.languages.sourceLanguage] ?? '');
   const [output, setOutput] = useState('');
   const [busy, setBusy] = useState(false);
   const [runError, setRunError] = useState<string | null>(null);
   const [elapsedMs, setElapsedMs] = useState<number | null>(null);
 
-  const selectPair = (i: number) => {
-    if (i === selected) return;
+  const select = (nextFamily: number, nextPair: number) => {
+    if (nextFamily === family && nextPair === selected) return;
     translateStop?.();
-    setSelected(i);
-    setText(sampleFor(PAIRS[i]!.value));
+    setFamily(nextFamily);
+    setSelected(nextPair);
+    const source = FAMILIES[nextFamily]!.pairs[nextPair]!.languages.sourceLanguage;
+    setText(SAMPLES[source] ?? '');
     setOutput('');
     setRunError(null);
     setElapsedMs(null);
@@ -67,7 +99,9 @@ function TranslationContent() {
     setElapsedMs(null);
     try {
       const startedAt = Date.now();
-      const result = await translate(text, (piece) => setOutput((prev) => prev + piece));
+      const result = await translate(text, active.languages, (piece) =>
+        setOutput((prev) => prev + piece)
+      );
       setElapsedMs(Date.now() - startedAt);
       setOutput(result);
     } catch (e: any) {
@@ -78,6 +112,24 @@ function TranslationContent() {
     }
   };
 
+  const chips = (labels: string[], current: number, onPress: (i: number) => void) => (
+    <ScrollView
+      horizontal
+      showsHorizontalScrollIndicator={false}
+      contentContainerStyle={styles.chipRow}
+    >
+      {labels.map((label, i) => (
+        <TouchableOpacity
+          key={label}
+          style={[styles.chip, i === current && styles.chipActive]}
+          onPress={() => onPress(i)}
+        >
+          <Text style={[styles.chipText, i === current && styles.chipTextActive]}>{label}</Text>
+        </TouchableOpacity>
+      ))}
+    </ScrollView>
+  );
+
   return (
     <KeyboardAvoidingView
       style={styles.flex}
@@ -86,29 +138,21 @@ function TranslationContent() {
       <ScrollView style={styles.container} contentContainerStyle={styles.content}>
         <View style={styles.card}>
           <Text style={styles.cardTitle}>Translation</Text>
-          <Text style={styles.cardDescription}>
-            On-device Opus-MT translation. Each model covers one language pair and translates the
-            text a sentence at a time, streaming the result as it is decoded.
-          </Text>
+          <Text style={styles.cardDescription}>{description}</Text>
+
+          <Text style={styles.fieldLabel}>Model</Text>
+          {chips(
+            FAMILIES.map((f) => f.label),
+            family,
+            (i) => select(i, 0)
+          )}
 
           <Text style={styles.fieldLabel}>Language pair</Text>
-          <ScrollView
-            horizontal
-            showsHorizontalScrollIndicator={false}
-            contentContainerStyle={styles.chipRow}
-          >
-            {PAIRS.map((pair, i) => (
-              <TouchableOpacity
-                key={pair.label}
-                style={[styles.chip, i === selected && styles.chipActive]}
-                onPress={() => selectPair(i)}
-              >
-                <Text style={[styles.chipText, i === selected && styles.chipTextActive]}>
-                  {pair.label}
-                </Text>
-              </TouchableOpacity>
-            ))}
-          </ScrollView>
+          {chips(
+            pairs.map((p) => p.label),
+            selected,
+            (i) => select(family, i)
+          )}
 
           <ModelStatus
             isReady={isReady}
diff --git a/docs/docs/02-extensions/natural-language/07-translation.md b/docs/docs/02-extensions/natural-language/07-translation.md
index f044fd9b69..65b4e828ef 100644
--- a/docs/docs/02-extensions/natural-language/07-translation.md
+++ b/docs/docs/02-extensions/natural-language/07-translation.md
@@ -1,17 +1,30 @@
 ---
 title: Translation
 slug: /extensions/translation
-description: 'Translate text between languages fully on-device in React Native with Opus-MT models.'
-keywords: [react native, translation, machine translation, opus-mt, marian, mobile ml, on-device ai]
+description: 'Translate text between languages fully on-device in React Native with Opus-MT and EuroLLM models.'
+keywords:
+  [
+    react native,
+    translation,
+    machine translation,
+    opus-mt,
+    marian,
+    eurollm,
+    mobile ml,
+    on-device ai,
+  ]
 ---
 
 # Translation
 
-Translation models turn text in one language into another without sending it off the device. Each [Opus-MT](https://github.com/Helsinki-NLP/Opus-MT) model translates one fixed language pair, such as English to German.
+Translation models turn text in one language into another without sending it off the device. Two kinds are available behind the same API:
+
+- [Opus-MT](https://github.com/Helsinki-NLP/Opus-MT): small (~110 MB) and fast, one model per language pair, such as English to German.
+- [EuroLLM-1.7B-Instruct](https://huggingface.co/utter-project/EuroLLM-1.7B-Instruct): one 1.7 GB model that translates between any two of its 35 languages.
 
 ## Quick Start
 
-The [`useTranslator`](../../06-api-reference/functions/useTranslator.md) hook downloads the `.pte` model and tokenizer, loads the pipeline, and manages its lifecycle:
+The [`useTranslator`](../../06-api-reference/functions/useTranslator.md) hook downloads the `.pte` model and tokenizer, loads the pipeline, and manages its lifecycle. Every call names its language pair as ISO 639-1 codes:
 
 ```tsx
 import { models, useTranslator } from 'react-native-executorch';
@@ -27,64 +40,77 @@ function MyComponent() {
   const handleTranslate = async (text: string) => {
     if (!translator.isReady || !translator.translate) return;
 
-    const german = await translator.translate(text);
+    const german = await translator.translate(text, { sourceLanguage: 'en', targetLanguage: 'de' });
     console.log(german);
   };
 }
 ```
 
+An Opus-MT model accepts only its own pair. With `models.translation.EUROLLM_1_7B.DEFAULT`, the pair can change on every call without reloading the model.
+
 ## Streaming
 
 Pass a callback to receive the translation as it is decoded. Each call gets the newly decoded piece of text; joined together, the pieces equal the returned translation.
 
 ```typescript
 let partial = '';
-const result = await translator.translate('How are you? I am fine.', (piece) => {
+const result = await translator.translate('How are you? I am fine.', languages, (piece) => {
   partial += piece;
   setText(partial);
 });
 ```
 
-Call [`translateStop()`](../../06-api-reference/type-aliases/MarianTranslator.md#translatestop) to cancel; [`translate()`](../../06-api-reference/type-aliases/MarianTranslator.md#translate) then resolves with the text translated so far.
+Call [`translateStop()`](../../06-api-reference/type-aliases/Translator.md#translatestop) to cancel; [`translate()`](../../06-api-reference/type-aliases/Translator.md#translate) then resolves with the text translated so far.
 
 ## How Input Is Processed
 
-Opus-MT models are trained on single sentences, so the input is split after sentence-ending punctuation (`.`, `!`, `?`) and at line breaks, and each sentence is translated on its own. Line breaks are kept in the output. A single sentence longer than the model's maximum source length (256 tokens) is truncated, and one sentence translates to at most 256 tokens.
+Line breaks are kept in the output for both kinds of model.
+
+- **Opus-MT** models are trained on single sentences, so the input is split after sentence-ending punctuation (`.`, `!`, `?`) and at line breaks, and each sentence is translated on its own. A single sentence longer than the model's maximum source length (256 tokens) is truncated, and one sentence translates to at most 256 tokens.
+- **EuroLLM** translates each line on its own with the model card's prompt, decoding greedily. A line and its translation together must fit the 1024-token context.
+
+EuroLLM supports Arabic (`ar`), Bulgarian (`bg`), Catalan (`ca`), Chinese (`zh`), Croatian (`hr`), Czech (`cs`), Danish (`da`), Dutch (`nl`), English (`en`), Estonian (`et`), Finnish (`fi`), French (`fr`), Galician (`gl`), German (`de`), Greek (`el`), Hindi (`hi`), Hungarian (`hu`), Irish (`ga`), Italian (`it`), Japanese (`ja`), Korean (`ko`), Latvian (`lv`), Lithuanian (`lt`), Maltese (`mt`), Norwegian (`no`), Polish (`pl`), Portuguese (`pt`), Romanian (`ro`), Russian (`ru`), Slovak (`sk`), Slovenian (`sl`), Spanish (`es`), Swedish (`sv`), Turkish (`tr`) and Ukrainian (`uk`).
 
 ## Imperative API
 
-For use outside React components, create the pipeline with [`createMarianTranslator`](../../06-api-reference/functions/createMarianTranslator.md):
+For use outside React components, create the pipeline with [`createMarianTranslator`](../../06-api-reference/functions/createMarianTranslator.md) or [`createLLMTranslator`](../../06-api-reference/functions/createLLMTranslator.md):
 
 ```typescript
-import { createMarianTranslator, download, models } from 'react-native-executorch';
+import { createLLMTranslator, download, models } from 'react-native-executorch';
 
-const model = await download(models.translation.OPUS_MT_EN_FR.DEFAULT);
-const translator = await createMarianTranslator(model);
+const model = await download(models.translation.EUROLLM_1_7B.DEFAULT);
+const translator = await createLLMTranslator(model);
 
 try {
-  console.log(await translator.translate('The weather is nice today.'));
+  console.log(
+    await translator.translate('The weather is nice today.', {
+      sourceLanguage: 'en',
+      targetLanguage: 'pl',
+    })
+  );
 } finally {
   translator.dispose();
 }
 ```
 
-[`translateWorklet`](../../06-api-reference/type-aliases/MarianTranslator.md#translateworklet) runs the same pipeline synchronously on a worklet runtime. See [Worklets & Threading](../../03-core-and-advanced/06-worklets-and-threading.md).
+[`translateWorklet`](../../06-api-reference/type-aliases/MarianTranslator.md#translateworklet) runs the Opus-MT pipeline synchronously on a worklet runtime. See [Worklets & Threading](../../03-core-and-advanced/06-worklets-and-threading.md).
 
 ## Available Models
 
 The models are available in [`models.translation`](../../06-api-reference/variables/models.md#translation):
 
-| Model           | Direction         | Size   | Supported Backends |
-| :-------------- | :---------------- | :----- | :----------------- |
-| `OPUS_MT_EN_DE` | English → German  | 107 MB | XNNPACK (CPU)      |
-| `OPUS_MT_DE_EN` | German → English  | 107 MB | XNNPACK (CPU)      |
-| `OPUS_MT_EN_ES` | English → Spanish | 114 MB | XNNPACK (CPU)      |
-| `OPUS_MT_ES_EN` | Spanish → English | 114 MB | XNNPACK (CPU)      |
-| `OPUS_MT_EN_FR` | English → French  | 108 MB | XNNPACK (CPU)      |
-| `OPUS_MT_FR_EN` | French → English  | 108 MB | XNNPACK (CPU)      |
+| Model           | Direction               | Size   | Supported Backends            |
+| :-------------- | :---------------------- | :----- | :---------------------------- |
+| `OPUS_MT_EN_DE` | English → German        | 107 MB | XNNPACK (CPU)                 |
+| `OPUS_MT_DE_EN` | German → English        | 107 MB | XNNPACK (CPU)                 |
+| `OPUS_MT_EN_ES` | English → Spanish       | 114 MB | XNNPACK (CPU)                 |
+| `OPUS_MT_ES_EN` | Spanish → English       | 114 MB | XNNPACK (CPU)                 |
+| `OPUS_MT_EN_FR` | English → French        | 108 MB | XNNPACK (CPU)                 |
+| `OPUS_MT_FR_EN` | French → English        | 108 MB | XNNPACK (CPU)                 |
+| `EUROLLM_1_7B`  | Any of its 35 languages | 1.7 GB | XNNPACK (CPU), MLX (iOS, GPU) |
 
 :::info License
-`OPUS_MT_EN_DE` is licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/) and requires attribution to the [Helsinki-NLP Opus-MT](https://huggingface.co/Helsinki-NLP/opus-mt-en-de) project. The other pairs are Apache-2.0.
+`OPUS_MT_EN_DE` is licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/) and requires attribution to the [Helsinki-NLP Opus-MT](https://huggingface.co/Helsinki-NLP/opus-mt-en-de) project. The other Opus-MT pairs and EuroLLM are Apache-2.0.
 :::
 
 ## API Reference
@@ -93,11 +119,16 @@ The models are available in [`models.translation`](../../06-api-reference/variab
 
 - [`useTranslator()`](../../06-api-reference/functions/useTranslator.md) — React hook for translation model downloading, state, and lifecycle.
 - [`createMarianTranslator()`](../../06-api-reference/functions/createMarianTranslator.md) — Imperative factory for Opus-MT translation pipelines.
+- [`createLLMTranslator()`](../../06-api-reference/functions/createLLMTranslator.md) — Imperative factory for EuroLLM translation pipelines.
 
 ### Types
 
-- [`MarianTranslator`](../../06-api-reference/type-aliases/MarianTranslator.md) — Translator runner interface ([`translate`](../../06-api-reference/type-aliases/MarianTranslator.md#translate), [`translateWorklet`](../../06-api-reference/type-aliases/MarianTranslator.md#translateworklet), [`translateStop`](../../06-api-reference/type-aliases/MarianTranslator.md#translatestop)).
-- [`MarianTranslatorModel`](../../06-api-reference/type-aliases/MarianTranslatorModel.md) — Model configuration with model path, tokenizer path, and language pair.
+- [`Translator`](../../06-api-reference/type-aliases/Translator.md) — Translator runner interface ([`translate`](../../06-api-reference/type-aliases/Translator.md#translate), [`translateStop`](../../06-api-reference/type-aliases/Translator.md#translatestop)).
+- [`TranslationLanguages`](../../06-api-reference/type-aliases/TranslationLanguages.md) — Source and target language of one call.
+- [`TranslatorModel`](../../06-api-reference/type-aliases/TranslatorModel.md) — Any translation model configuration.
+- [`MarianTranslator`](../../06-api-reference/type-aliases/MarianTranslator.md) — Opus-MT runner, which adds [`translateWorklet`](../../06-api-reference/type-aliases/MarianTranslator.md#translateworklet).
+- [`MarianTranslatorModel`](../../06-api-reference/type-aliases/MarianTranslatorModel.md) — Opus-MT configuration with model path, tokenizer path, and language pair.
+- [`LLMTranslatorModel`](../../06-api-reference/type-aliases/LLMTranslatorModel.md) — EuroLLM configuration with model, tokenizer, and tokenizer config paths.
 
 ### Model Presets
 
@@ -107,4 +138,5 @@ The models are available in [`models.translation`](../../06-api-reference/variab
 View the implementation on GitHub:
 
 - [`src/extensions/nlp/tasks/marianTranslation.ts` ↗](https://github.com/software-mansion/react-native-executorch/blob/main/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts)
+- [`src/extensions/llm/tasks/llmTranslation.ts` ↗](https://github.com/software-mansion/react-native-executorch/blob/main/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts)
   :::
diff --git a/docs/docs/03-core-and-advanced/08-native-libraries.md b/docs/docs/03-core-and-advanced/08-native-libraries.md
index 0aed2243dc..df8e712c42 100644
--- a/docs/docs/03-core-and-advanced/08-native-libraries.md
+++ b/docs/docs/03-core-and-advanced/08-native-libraries.md
@@ -90,7 +90,7 @@ Specifying a task under `features` is shorthand: it automatically expands to the
 | `speechToText`         | xnnpack, coreml, mlx, vulkan | —                   |
 | `textToSpeech`         | xnnpack, coreml, mlx, vulkan | phonemis            |
 | `vad`                  | xnnpack                      | —                   |
-| `translation`          | xnnpack                      | —                   |
+| `translation`          | xnnpack, mlx                 | —                   |
 | `textEmbeddings`       | xnnpack, coreml, mlx, vulkan | —                   |
 | `imageEmbeddings`      | xnnpack, coreml, mlx, vulkan | opencv              |
 | `classification`       | xnnpack, coreml              | opencv              |
diff --git a/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap b/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap
index eeb42ce0de..9a05bbb096 100644
--- a/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap
+++ b/packages/react-native-executorch/__tests__/api/__snapshots__/apiSurface.test.ts.snap
@@ -147,6 +147,7 @@ exports[`public API surface matches the recorded export list 1`] = `
   "createKeypointDetector",
   "createKokoroTextToSpeech",
   "createLLMChatSession",
+  "createLLMTranslator",
   "createMarianTranslator",
   "createObjectDetector",
   "createPaddleOcr",
diff --git a/packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts b/packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts
new file mode 100644
index 0000000000..e6e5a185e2
--- /dev/null
+++ b/packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts
@@ -0,0 +1,123 @@
+/**
+ * The LLM (EuroLLM) translator.
+ *
+ * It runs on the real chat session and LLM runner; only the `.pte` below them
+ * is scripted (see `support/fakeLLM.ts`), so a test sees the exact prompt each
+ * line was sent with.
+ */
+import { createLLMTranslator } from '../../src/extensions/llm/tasks/llmTranslation';
+import { fakeJsi } from '../support/fakeJsi';
+import { fakeFs } from '../support/blobUtilMock';
+import { tracked } from '../support/lifetime';
+import { registerFakeLLM, type FakeGeneration } from '../support/fakeLLM';
+
+const MODEL_PATH = '/models/eurollm.pte';
+const TOKENIZER_PATH = '/models/tokenizer.json';
+const TOKENIZER_CONFIG_PATH = '/models/tokenizer_config.json';
+const EOS = '<|im_end|>';
+
+// EuroLLM-1.7B-Instruct's published chat template.
+const CHAT_TEMPLATE =
+  "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}<|im_start|>system\n{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] }}{% endif %}<|im_end|>\n{% for message in messages %}{% if message['role'] != 'system' %}<|im_start|>{{ message['role'] }}\n{{ message['content'] }}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}";
+
+const config = {
+  name: 'eurollm' as const,
+  modelPath: MODEL_PATH,
+  tokenizerPath: TOKENIZER_PATH,
+  tokenizerConfigPath: TOKENIZER_CONFIG_PATH,
+};
+
+const EN_DE = { sourceLanguage: 'en', targetLanguage: 'de' };
+
+let llm: ReturnType<typeof registerFakeLLM>;
+
+/** Registers the model, answering with `responses` in order, one per line. */
+const script = (...responses: string[]) => {
+  const generations: FakeGeneration[] = responses.map((response) => ({ response }));
+  llm = registerFakeLLM(MODEL_PATH, TOKENIZER_PATH, { eosToken: EOS, generations });
+};
+
+// The fake tokenizer splits on whitespace, so prompts are compared with every
+// whitespace run collapsed to one space.
+const squash = (text: string) => text.replace(/\s+/g, ' ').trim();
+const promptsSent = (): string[] => llm.prompts().map((prompt) => squash(prompt.text));
+const userTurn = (source: string, target: string, line: string) =>
+  squash(
+    `<|im_start|>system\n<|im_end|>\n<|im_start|>user\n` +
+      `Translate the following ${source} source text to ${target}:\n` +
+      `${source}: ${line} \n${target}: <|im_end|>\n<|im_start|>assistant\n`
+  );
+
+beforeEach(() => {
+  // The keys are the published `tokenizer_config.json` field names.
+  /* eslint-disable camelcase */
+  fakeFs.write(
+    TOKENIZER_CONFIG_PATH,
+    JSON.stringify({ chat_template: CHAT_TEMPLATE, eos_token: EOS })
+  );
+  /* eslint-enable camelcase */
+  script('Hallo Welt.');
+});
+
+describe('createLLMTranslator', () => {
+  it('sends each line with the model card prompt and keeps line breaks', async () => {
+    script('Hallo Welt.', 'Guten Morgen.');
+    const translator = tracked(await createLLMTranslator(config));
+
+    const text = await translator.translate('Hello world.\n\nGood morning.', EN_DE);
+
+    expect(text).toBe('Hallo Welt.\n\nGuten Morgen.');
+    // Each line starts from an empty cache, without the lines before it.
+    expect(promptsSent()).toEqual([
+      userTurn('English', 'German', 'Hello world.'),
+      userTurn('English', 'German', 'Good morning.'),
+    ]);
+  });
+
+  it('translates any supported pair with the same model', async () => {
+    const translator = tracked(await createLLMTranslator(config));
+
+    await translator.translate('Dzień dobry.', { sourceLanguage: 'pl', targetLanguage: 'en' });
+
+    expect(promptsSent()).toEqual([userTurn('Polish', 'English', 'Dzień dobry.')]);
+  });
+
+  it('drops the whitespace the reply starts with', async () => {
+    script(' Hallo');
+    const translator = tracked(await createLLMTranslator(config));
+
+    expect(await translator.translate('Hello', EN_DE)).toBe('Hallo');
+  });
+
+  it('streams pieces that add up to the translation', async () => {
+    script('Hallo Welt.', 'Guten Morgen.');
+    const translator = tracked(await createLLMTranslator(config));
+    const pieces: string[] = [];
+
+    const text = await translator.translate('Hello world.\nGood morning.', EN_DE, (piece) =>
+      pieces.push(piece)
+    );
+    // Pieces are delivered on the RN thread, which the mock defers to a macrotask.
+    await new Promise((resolve) => setTimeout(resolve, 0));
+
+    expect(pieces.join('')).toBe(text);
+  });
+
+  it('rejects a language the model does not know', async () => {
+    const translator = tracked(await createLLMTranslator(config));
+
+    await expect(
+      translator.translate('Hello', { sourceLanguage: 'en', targetLanguage: 'xx' })
+    ).rejects.toThrow(/unsupported language 'xx'/);
+  });
+
+  it('releases everything on dispose', async () => {
+    const translator = tracked(await createLLMTranslator(config));
+    await translator.translate('Hello world.', EN_DE);
+    translator.dispose();
+
+    expect(fakeJsi.liveTensors()).toBe(0);
+    expect(fakeJsi.liveModels()).toEqual([]);
+    expect(fakeJsi.liveTokenizers()).toEqual([]);
+  });
+});
diff --git a/packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts b/packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts
index 9969117de3..cf9a5889b3 100644
--- a/packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts
+++ b/packages/react-native-executorch/__tests__/tasks/marianTranslation.test.ts
@@ -42,6 +42,8 @@ function marianSchema(source: ConcreteDim) {
   });
 }
 
+const EN_DE = { sourceLanguage: 'en', targetLanguage: 'de' };
+
 const read = (t: FakeTensor) => Array.from({ length: t.numel }, (_, i) => t.getElement(i));
 
 /** What each `encode` received, and the decoder inputs of each step. */
@@ -79,7 +81,7 @@ describe('createMarianTranslator', () => {
     register(RangeDim(1, 8));
     const translator = tracked(await createMarianTranslator(config));
 
-    expect(await translator.translate('hello world')).toBe('hallo welt');
+    expect(await translator.translate('hello world', EN_DE)).toBe('hallo welt');
     expect(encoded).toEqual([{ ids: [2, 3, EOS], mask: [1, 1, 1] }]);
     expect(decoded).toEqual([
       { token: PAD, position: 0 },
@@ -93,7 +95,7 @@ describe('createMarianTranslator', () => {
     fakeJsi.registerTokenizer(TOKENIZER_PATH, { tokens: VOCAB, suffix: [EOS] });
     const translator = tracked(await createMarianTranslator(config));
 
-    await translator.translate('hello world');
+    await translator.translate('hello world', EN_DE);
     expect(encoded[0]!.ids).toEqual([2, 3, EOS]);
   });
 
@@ -101,7 +103,7 @@ describe('createMarianTranslator', () => {
     register(RangeDim(6, 6));
     const translator = tracked(await createMarianTranslator(config));
 
-    expect(await translator.translate('hello world')).toBe('hallo welt');
+    expect(await translator.translate('hello world', EN_DE)).toBe('hallo welt');
     expect(encoded).toEqual([{ ids: [2, 3, EOS, PAD, PAD, PAD], mask: [1, 1, 1, 0, 0, 0] }]);
   });
 
@@ -109,7 +111,7 @@ describe('createMarianTranslator', () => {
     register(RangeDim(1, 4));
     const translator = tracked(await createMarianTranslator(config));
 
-    await translator.translate('hello world hello world hello');
+    await translator.translate('hello world hello world hello', EN_DE);
     expect(encoded[0]!.ids).toEqual([2, 3, 2, EOS]);
   });
 
@@ -117,7 +119,7 @@ describe('createMarianTranslator', () => {
     register(RangeDim(1, 8));
     const translator = tracked(await createMarianTranslator(config));
 
-    const text = await translator.translate('hello. world!\n\nhello');
+    const text = await translator.translate('hello. world!\n\nhello', EN_DE);
     expect(text).toBe('hallo welt hallo welt\n\nhallo welt');
     expect(encoded).toHaveLength(3);
   });
@@ -127,7 +129,7 @@ describe('createMarianTranslator', () => {
     const translator = tracked(await createMarianTranslator(config));
     const pieces: string[] = [];
 
-    const text = await translator.translate('hello world', (piece) => pieces.push(piece));
+    const text = await translator.translate('hello world', EN_DE, (piece) => pieces.push(piece));
     // Pieces are delivered on the RN thread, which the mock defers to a macrotask.
     await new Promise((resolve) => setTimeout(resolve, 0));
     expect(pieces.join('')).toBe(text);
@@ -138,10 +140,19 @@ describe('createMarianTranslator', () => {
     register(RangeDim(1, 8), Array(300).fill(HALLO));
     const translator = tracked(await createMarianTranslator(config));
 
-    await translator.translate('hello');
+    await translator.translate('hello', EN_DE);
     expect(decoded).toHaveLength(256);
   });
 
+  it("rejects a language pair other than the model's own", async () => {
+    register(RangeDim(1, 8));
+    const translator = tracked(await createMarianTranslator(config));
+
+    await expect(
+      translator.translate('hello', { sourceLanguage: 'de', targetLanguage: 'en' })
+    ).rejects.toThrow(/only translates en to de/);
+  });
+
   it('rejects a model without the source-length constraints', async () => {
     const kv = Array(NUM_CROSS_KV).fill(f32(2, RangeDim(1, 8), 4));
     fakeJsi.registerModel(MODEL_PATH, {
@@ -164,7 +175,7 @@ describe('createMarianTranslator', () => {
   it('releases everything on dispose', async () => {
     register(RangeDim(1, 8));
     const translator = tracked(await createMarianTranslator(config));
-    await translator.translate('hello world. hello');
+    await translator.translate('hello world. hello', EN_DE);
     translator.dispose();
 
     expect(fakeJsi.liveTensors()).toBe(0);
diff --git a/packages/react-native-executorch/scripts/download-libs.js b/packages/react-native-executorch/scripts/download-libs.js
index 4366be922c..1873b0db42 100644
--- a/packages/react-native-executorch/scripts/download-libs.js
+++ b/packages/react-native-executorch/scripts/download-libs.js
@@ -143,7 +143,7 @@ const FEATURE_MAP = {
   // FSMN VAD — xnnpack only.
   vad: { backends: ['xnnpack'], libs: [] },
   // Opus-MT ships xnnpack int8 only: it beat Core ML, MLX and Vulkan on device.
-  translation: { backends: ['xnnpack'], libs: [] },
+  translation: { backends: ['xnnpack', 'mlx'], libs: [] },
   // The MiniLM/CLIP-text/distiluse family ships coreml alongside xnnpack,
   // LFM2.5-Embedding and distiluse add MLX iOS exports, and every sentence
   // transformer now ships a vulkan Android export.
diff --git a/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts b/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts
new file mode 100644
index 0000000000..bd1761431c
--- /dev/null
+++ b/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts
@@ -0,0 +1,228 @@
+/**
+ * Instruction-tuned LLM (EuroLLM) machine translation task pipeline.
+ */
+
+import { scheduleOnRN, type WorkletRuntime } from 'react-native-worklets';
+import RNBlobUtil from 'react-native-blob-util';
+
+import { wrapAsync } from '../../../core/runtime';
+import { RnExecuTorchError } from '../../../core/error';
+import { createResourceScope } from '../../../core/lifetime';
+import type { TranslationLanguages, Translator } from '../../nlp/utils/translationUtils';
+import {
+  createLLMRunner,
+  type LLMGenerationConfig,
+  type LLMRunner,
+  type Prompt,
+} from '../llmRunner';
+import { parseTokenizerConfig } from '../utils/tokenizerConfig';
+import { createChatPreprocessor } from '../utils/chatPreprocessor';
+import type { LLMModel } from './llmChatSession';
+
+// Languages EuroLLM was trained on, keyed by ISO 639-1 code. The prompt names
+// them in English, as in the model card.
+const EUROLLM_LANGUAGES: Readonly<Record<string, string>> = {
+  ar: 'Arabic',
+  bg: 'Bulgarian',
+  ca: 'Catalan',
+  cs: 'Czech',
+  da: 'Danish',
+  de: 'German',
+  el: 'Greek',
+  en: 'English',
+  es: 'Spanish',
+  et: 'Estonian',
+  fi: 'Finnish',
+  fr: 'French',
+  ga: 'Irish',
+  gl: 'Galician',
+  hi: 'Hindi',
+  hr: 'Croatian',
+  hu: 'Hungarian',
+  it: 'Italian',
+  ja: 'Japanese',
+  ko: 'Korean',
+  lt: 'Lithuanian',
+  lv: 'Latvian',
+  mt: 'Maltese',
+  nl: 'Dutch',
+  no: 'Norwegian',
+  pl: 'Polish',
+  pt: 'Portuguese',
+  ro: 'Romanian',
+  ru: 'Russian',
+  sk: 'Slovak',
+  sl: 'Slovenian',
+  sv: 'Swedish',
+  tr: 'Turkish',
+  uk: 'Ukrainian',
+  zh: 'Chinese',
+};
+
+/**
+ * Paths required to instantiate an LLM translator. One model translates
+ * between any two of its supported languages.
+ * @category NLP / Types
+ */
+export type LLMTranslatorModel = LLMModel & {
+  /** Identifies the pipeline this config belongs to. */
+  readonly name: 'eurollm';
+};
+
+const languageName = (code: string): string => {
+  const name = EUROLLM_LANGUAGES[code];
+  if (!name) {
+    throw RnExecuTorchError('INVALID_ARGUMENT', `translate: unsupported language '${code}'.`);
+  }
+  return name;
+};
+
+function generateWorklet(
+  runner: LLMRunner,
+  prompt: Prompt,
+  genConfig: LLMGenerationConfig,
+  stopTokens: readonly string[],
+  onToken?: (token: string) => void
+): string {
+  'worklet';
+  let response = '';
+  runner.generate(prompt, genConfig, (token) => {
+    if (stopTokens.includes(token)) return;
+    response += token;
+    if (onToken) scheduleOnRN(onToken, token);
+  });
+  return response;
+}
+
+// Greedy decoding, as in the model card's evaluation.
+const GENERATION_CONFIG: LLMGenerationConfig = { temperature: 0 };
+
+/**
+ * Creates a translator on top of an instruction-tuned LLM such as EuroLLM.
+ *
+ * Every line is sent as its own single-turn chat with the model card's
+ * translation prompt, from an empty KV cache, and decoded greedily. One model
+ * translates between any two of its languages, so the pair can change per
+ * call.
+ * @category NLP / Tasks
+ * @param config Model, tokenizer and tokenizer config paths. See
+ * {@link LLMTranslatorModel}.
+ * @param runtime Optional worklet runtime thread on which to run the model
+ * execution.
+ * @returns A promise resolving to the instantiated {@link Translator}.
+ * @throws {RnExecuTorchError} With code `LOAD_FAILED` if the model or
+ * tokenizer fails to load, or `SCHEMA_MISMATCH` if the model schema does not
+ * match a text LLM.
+ */
+export async function createLLMTranslator(
+  config: LLMTranslatorModel,
+  runtime?: WorkletRuntime
+): Promise<Translator> {
+  const scope = createResourceScope();
+  const dispose = scope.dispose;
+
+  try {
+    const { modelPath, tokenizerPath, tokenizerConfigPath } = config;
+    const tokenizerConfigStr = await RNBlobUtil.fs.readFile(tokenizerConfigPath, 'utf8');
+    const { chatTemplate, bosToken, eosToken, stopTokens } = parseTokenizerConfig(
+      JSON.parse(tokenizerConfigStr)
+    );
+    const chatPreprocessor = scope.track(
+      createChatPreprocessor({ chatTemplate, bosToken, eosToken })
+    );
+    // prettier-ignore
+    const runner = scope.track(await createLLMRunner(modelPath, tokenizerPath, undefined, runtime));
+    const generate = wrapAsync(generateWorklet, runtime);
+
+    let busy = false;
+    let stopped = false;
+
+    const translateLine = async (
+      line: string,
+      source: string,
+      target: string,
+      onPiece: (piece: string) => void
+    ): Promise<string> => {
+      const content =
+        `Translate the following ${source} source text to ${target}:\n` +
+        `${source}: ${line} \n${target}: `;
+      runner.reset();
+      const prompt = chatPreprocessor.process([{ role: 'user', content }], 1, {
+        addGenPrompt: true,
+      });
+      try {
+        let started = false;
+        const response = await generate(runner, prompt, GENERATION_CONFIG, stopTokens, (token) => {
+          const piece = started ? token : token.trimStart();
+          if (piece === '') return;
+          started = true;
+          onPiece(piece);
+        });
+        return response.trimStart();
+      } finally {
+        chatPreprocessor.clear();
+      }
+    };
+
+    const translate = async (
+      text: string,
+      languages: TranslationLanguages,
+      onToken?: (token: string) => void
+    ): Promise<string> => {
+      const source = languageName(languages.sourceLanguage);
+      const target = languageName(languages.targetLanguage);
+      if (busy) {
+        throw RnExecuTorchError('RESOURCE_BUSY', 'translate: A translation is in progress.');
+      }
+
+      busy = true;
+      stopped = false;
+      let output = '';
+      // Text between translated lines (line breaks, blank lines) is streamed
+      // ahead of the next translated piece, so the pieces keep their order.
+      let pending = '';
+
+      try {
+        // Odd indices hold the line breaks themselves.
+        const parts = text.split(/(\n+)/);
+        for (let i = 0; i < parts.length && !stopped; i++) {
+          const part = parts[i]!;
+          const line = part.trim();
+          if (i % 2 === 1 || line === '') {
+            output += part;
+            pending += part;
+            continue;
+          }
+
+          const lead = part.slice(0, part.length - part.trimStart().length);
+          const trail = part.slice(part.trimEnd().length);
+          // Pieces arrive later on the RN thread, so each line captures the
+          // separator it streams ahead of its first piece.
+          const prefix = pending + lead;
+          let first = true;
+          const translated = await translateLine(line, source, target, (piece) => {
+            onToken?.(first ? prefix + piece : piece);
+            first = false;
+          });
+          output += lead + translated + trail;
+          pending = translated === '' ? prefix + trail : trail;
+        }
+        if (!stopped && pending !== '') onToken?.(pending);
+        return output;
+      } finally {
+        busy = false;
+      }
+    };
+
+    const translateStop = () => {
+      if (!busy) return;
+      stopped = true;
+      runner.stop();
+    };
+
+    return { dispose, translate, translateStop };
+  } catch (error) {
+    dispose();
+    throw error;
+  }
+}
diff --git a/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts b/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts
index 4ebcd24113..424d7e0053 100644
--- a/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts
+++ b/packages/react-native-executorch/src/extensions/nlp/tasks/marianTranslation.ts
@@ -20,7 +20,12 @@ import { createResourceScope } from '../../../core/lifetime';
 
 import { argmax } from '../../math';
 import { loadTokenizer } from '../tokenizer';
-import { splitSentences } from '../utils/translationUtils';
+import { RnExecuTorchError } from '../../../core/error';
+import {
+  splitSentences,
+  type TranslationLanguages,
+  type Translator,
+} from '../utils/translationUtils';
 
 // Positions in the decoder's self-attention KV cache, i.e. the most tokens one
 // sentence can translate to.
@@ -47,39 +52,20 @@ export type MarianTranslatorModel = {
 };
 
 /**
- * Marian (Opus-MT) translation task runner.
+ * Marian (Opus-MT) translation task runner. The text is split into sentences,
+ * which are translated one at a time.
  * @category NLP / Types
  */
-export type MarianTranslator = {
-  /**
-   * Releases all allocated native resources.
-   */
-  readonly dispose: () => void;
-
+export type MarianTranslator = Translator & {
   /**
-   * Asynchronously translates text from the model's source language to its
-   * target language. The text is split into sentences, which are translated
-   * one at a time; line breaks are kept.
-   * @param text The text to translate.
-   * @param onToken Optional callback fired on the RN thread with each newly
-   * decoded piece of the translation.
-   * @returns A promise resolving to the translated text.
-   * @throws {RnExecuTorchError} With code `RESOURCE_BUSY` if the model is in
-   * use, or `RESOURCE_DISPOSED` if disposed.
+   * Synchronous version of {@link Translator.translate} to be executed
+   * directly on the caller or worklet thread.
    */
-  readonly translate: (text: string, onToken?: (token: string) => void) => Promise<string>;
-
-  /**
-   * Synchronous version of {@link translate} to be executed directly on the
-   * caller or worklet thread.
-   */
-  readonly translateWorklet: (text: string, onToken?: (token: string) => void) => string;
-
-  /**
-   * Interrupts an active translation call, which returns the text translated
-   * so far.
-   */
-  readonly translateStop: () => void;
+  readonly translateWorklet: (
+    text: string,
+    languages: TranslationLanguages,
+    onToken?: (token: string) => void
+  ) => string;
 };
 
 /**
@@ -219,8 +205,22 @@ export async function createMarianTranslator(
       }
     };
 
-    const translateWorklet = (text: string, onToken?: (token: string) => void): string => {
+    const { sourceLanguage, targetLanguage } = config;
+    const translateWorklet = (
+      text: string,
+      languages: TranslationLanguages,
+      onToken?: (token: string) => void
+    ): string => {
       'worklet';
+      if (
+        languages.sourceLanguage !== sourceLanguage ||
+        languages.targetLanguage !== targetLanguage
+      ) {
+        throw RnExecuTorchError(
+          'INVALID_ARGUMENT',
+          `translate: this model only translates ${sourceLanguage} to ${targetLanguage}.`
+        );
+      }
       isCancelled.setBlocking(false);
 
       const emit = (piece: string) => {
diff --git a/packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts b/packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts
index e5909a8c08..80110fe9a2 100644
--- a/packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts
+++ b/packages/react-native-executorch/src/extensions/nlp/utils/translationUtils.ts
@@ -1,7 +1,53 @@
 /**
- * Text segmentation shared by the translation pipelines.
+ * Types and text segmentation shared by the translation pipelines.
  */
 
+/**
+ * Source and target language of one translation, as ISO 639-1 codes.
+ * @category NLP / Types
+ */
+export type TranslationLanguages = {
+  /** ISO 639-1 code of the language to translate from. */
+  readonly sourceLanguage: string;
+  /** ISO 639-1 code of the language to translate to. */
+  readonly targetLanguage: string;
+};
+
+/**
+ * Translation task runner, shared by every translation pipeline.
+ * @category NLP / Types
+ */
+export type Translator = {
+  /**
+   * Releases all allocated native resources.
+   */
+  readonly dispose: () => void;
+
+  /**
+   * Asynchronously translates text. Line breaks are kept.
+   * @param text The text to translate.
+   * @param languages The source and target language. A model built for one
+   * language pair accepts only that pair.
+   * @param onToken Optional callback fired on the RN thread with each newly
+   * decoded piece of the translation.
+   * @returns A promise resolving to the translated text.
+   * @throws {RnExecuTorchError} With code `INVALID_ARGUMENT` if the model does
+   * not translate between `languages`, `RESOURCE_BUSY` if the model is in use,
+   * or `RESOURCE_DISPOSED` if disposed.
+   */
+  readonly translate: (
+    text: string,
+    languages: TranslationLanguages,
+    onToken?: (token: string) => void
+  ) => Promise<string>;
+
+  /**
+   * Interrupts an active translation call, which returns the text translated
+   * so far.
+   */
+  readonly translateStop: () => void;
+};
+
 /**
  * A sentence and the whitespace that followed it in the source text.
  * @category NLP / Types
diff --git a/packages/react-native-executorch/src/hooks/useTranslator.ts b/packages/react-native-executorch/src/hooks/useTranslator.ts
index ae784b299e..eac9fc9732 100644
--- a/packages/react-native-executorch/src/hooks/useTranslator.ts
+++ b/packages/react-native-executorch/src/hooks/useTranslator.ts
@@ -3,28 +3,41 @@ import { useResourceDownload, type ResourceOptions } from './useResourceDownload
 import {
   createMarianTranslator,
   type MarianTranslatorModel,
-  type MarianTranslator,
 } from '../extensions/nlp/tasks/marianTranslation';
+import {
+  createLLMTranslator,
+  type LLMTranslatorModel,
+} from '../extensions/llm/tasks/llmTranslation';
+import type { Translator } from '../extensions/nlp/utils/translationUtils';
 
 /**
- * React hook to load and run a Marian (Opus-MT) translation pipeline.
+ * Configuration of any translation pipeline.
+ * @category NLP / Types
+ */
+export type TranslatorModel = MarianTranslatorModel | LLMTranslatorModel;
+
+/**
+ * React hook to load and run a translation pipeline: Marian (Opus-MT), one
+ * model per language pair, or an LLM (EuroLLM) that translates between any two
+ * of its languages.
  *
  * This hook manages downloading (if remote URLs are provided) and loading the
  * model and tokenizer, tracking download progress and load errors, and
  * releasing native memory when the component unmounts or the configuration
  * changes.
  *
- * For imperative usage, see {@link createMarianTranslator}.
+ * For imperative usage, see {@link createMarianTranslator} and
+ * {@link createLLMTranslator}.
  * @category Hooks
- * @param config The translation model configuration.
- * See {@link MarianTranslatorModel}.
+ * @param config The translation model configuration. See
+ * {@link TranslatorModel}.
  * @param options Load and caching options. See {@link ResourceOptions}.
- * @returns The same object as {@link MarianTranslator} (without `dispose`),
+ * @returns The same object as {@link Translator} (without `dispose`),
  * combined with loading state and download progress.
- * @see {@link MarianTranslator}
+ * @see {@link Translator}
  */
-export function useTranslator(
-  config: MarianTranslatorModel,
+export function useTranslator<C extends TranslatorModel>(
+  config: C,
   options?: ResourceOptions
 ): {
   /** Whether the pipeline is loaded and ready to translate. */
@@ -34,20 +47,20 @@ export function useTranslator(
   /** Download progress across every asset, in percent. */
   downloadProgress: number;
   /** The config with every remote URL resolved to a local path. */
-  resource: MarianTranslatorModel | undefined;
+  resource: C | undefined;
   /** Translates text. Undefined until the pipeline is ready. */
-  translate: MarianTranslator['translate'] | undefined;
+  translate: Translator['translate'] | undefined;
   /** Cancels an in-flight translation. Undefined until the pipeline is ready. */
-  translateStop: MarianTranslator['translateStop'] | undefined;
-};
-
-export function useTranslator(config: MarianTranslatorModel, options?: ResourceOptions) {
+  translateStop: Translator['translateStop'] | undefined;
+} {
   // Each config names the pipeline it belongs to, so the factory is resolved
   // from that tag alone.
-  const factory = (translatorConfig: MarianTranslatorModel): Promise<MarianTranslator> => {
+  const factory = (translatorConfig: TranslatorModel): Promise<Translator> => {
     switch (translatorConfig.name) {
       case 'marian':
         return createMarianTranslator(translatorConfig);
+      case 'eurollm':
+        return createLLMTranslator(translatorConfig);
     }
   };
 
diff --git a/packages/react-native-executorch/src/index.ts b/packages/react-native-executorch/src/index.ts
index a9a81aff9a..b72969fd5a 100644
--- a/packages/react-native-executorch/src/index.ts
+++ b/packages/react-native-executorch/src/index.ts
@@ -87,6 +87,8 @@ export * from './extensions/cv/tasks/imageEmbedding';
 export * from './extensions/cv/tasks/sdxsTextToImage';
 export * from './extensions/cv/tasks/paddleOcr';
 export * from './extensions/llm/tasks/llmChatSession';
+export * from './extensions/llm/tasks/llmTranslation';
+export type { Translator, TranslationLanguages } from './extensions/nlp/utils/translationUtils';
 export * from './extensions/nlp/tasks/tokenization';
 export * from './extensions/nlp/tasks/textEmbedding';
 export * from './extensions/nlp/tasks/colbertEmbedding';
diff --git a/packages/react-native-executorch/src/models.ts b/packages/react-native-executorch/src/models.ts
index 50a0ba121d..b7a857851a 100644
--- a/packages/react-native-executorch/src/models.ts
+++ b/packages/react-native-executorch/src/models.ts
@@ -31,6 +31,7 @@ import type { TextEmbedderModel } from './extensions/nlp/tasks/textEmbedding';
 import type { ColbertEmbedderModel } from './extensions/nlp/tasks/colbertEmbedding';
 import type { PrivacyFilterModel } from './extensions/nlp/tasks/privacyFilter';
 import type { MarianTranslatorModel } from './extensions/nlp/tasks/marianTranslation';
+import type { LLMTranslatorModel } from './extensions/llm/tasks/llmTranslation';
 import type { FsmnVadModel } from './extensions/speech/tasks/fsmnVoiceActivityDetection';
 import type { SupertonicTtsModel } from './extensions/speech/tasks/supertonicTextToSpeech';
 import type { KokoroTtsModel } from './extensions/speech/tasks/kokoroTextToSpeech';
@@ -2200,6 +2201,21 @@ const OPUS_MT_FR_EN_XNNPACK_INT8: MarianTranslatorModel = {
   targetLanguage: 'en',
 };
 
+const EUROLLM_BASE_URL = `${BASE_URL}/EuroLLM-1.7B-Instruct-ExecuTorch/${NEXT_VERSION_TAG}/1_7b`;
+
+const EUROLLM_1_7B_XNNPACK_8DA8W: LLMTranslatorModel = {
+  name: 'eurollm',
+  modelPath: `${EUROLLM_BASE_URL}/xnnpack/eurollm_1_7b_xnnpack_8da8w.pte`,
+  tokenizerPath: `${EUROLLM_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${EUROLLM_BASE_URL}/tokenizer_config.json`,
+};
+const EUROLLM_1_7B_MLX_INT8: LLMTranslatorModel = {
+  name: 'eurollm',
+  modelPath: `${EUROLLM_BASE_URL}/mlx/eurollm_1_7b_mlx_int8.pte`,
+  tokenizerPath: `${EUROLLM_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${EUROLLM_BASE_URL}/tokenizer_config.json`,
+};
+
 // =============================================================================
 // LLMs
 // =============================================================================
@@ -3785,6 +3801,11 @@ export const models = {
     OPUS_MT_EN_FR: variants({ XNNPACK_INT8: OPUS_MT_EN_FR_XNNPACK_INT8 }),
     /** Opus-MT French to English. */
     OPUS_MT_FR_EN: variants({ XNNPACK_INT8: OPUS_MT_FR_EN_XNNPACK_INT8 }),
+    /** EuroLLM 1.7B Instruct: any two of its 35 languages with one model. */
+    EUROLLM_1_7B: variants({
+      XNNPACK_8DA8W: EUROLLM_1_7B_XNNPACK_8DA8W,
+      MLX_INT8: EUROLLM_1_7B_MLX_INT8,
+    }),
   },
 
   /**

From 42d84f51732a8f0c61f0cae62299824550369f40 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mateusz=20S=C5=82uszniak?= <mateusz.sluszniak@swmansion.com>
Date: Fri, 23 Oct 2026 14:09:38 +0200
Subject: [PATCH 3/6] fix(llm): keep word breaks when streaming generated
 tokens

---
 .../extensions/streamDecoding.test.ts         | 49 +++++++++++++++++++
 .../__tests__/support/fakeJsi.ts              | 16 +++++-
 .../__tests__/support/fakeLLM.ts              |  6 ++-
 .../__tests__/tasks/llmRunner.test.ts         |  8 ++-
 .../extensions/llm/runners/llmGemmaRunner.ts  |  7 ++-
 .../llm/runners/llmMultimodalRunner.ts        |  7 ++-
 .../extensions/llm/runners/llmTextRunner.ts   |  7 ++-
 .../extensions/llm/utils/streamDecoding.ts    | 45 +++++++++++++++++
 8 files changed, 136 insertions(+), 9 deletions(-)
 create mode 100644 packages/react-native-executorch/__tests__/extensions/streamDecoding.test.ts
 create mode 100644 packages/react-native-executorch/src/extensions/llm/utils/streamDecoding.ts

diff --git a/packages/react-native-executorch/__tests__/extensions/streamDecoding.test.ts b/packages/react-native-executorch/__tests__/extensions/streamDecoding.test.ts
new file mode 100644
index 0000000000..a8b09f025f
--- /dev/null
+++ b/packages/react-native-executorch/__tests__/extensions/streamDecoding.test.ts
@@ -0,0 +1,49 @@
+/**
+ * Streamed detokenization of LLM output.
+ */
+import { loadTokenizer } from '../../src/extensions/nlp';
+import { decodeStreamed } from '../../src/extensions/llm/utils/streamDecoding';
+import { fakeJsi } from '../support/fakeJsi';
+
+const TOKENIZER_PATH = '/models/tokenizer.json';
+
+/** Streams `ids` one at a time, as the runners do. */
+const stream = (tokenizer: Awaited<ReturnType<typeof loadTokenizer>>, ids: number[]) => {
+  const pieces: string[] = [];
+  let previous: Int32Array | undefined;
+  for (const id of ids) {
+    const pending = Int32Array.of(id);
+    const piece = decodeStreamed(tokenizer, previous, pending, false);
+    if (piece === undefined) continue;
+    pieces.push(piece);
+    previous = pending;
+  }
+  return pieces;
+};
+
+describe('decodeStreamed', () => {
+  it('keeps word breaks when the decoder strips a leading space', async () => {
+    // SentencePiece pieces carry their word break in front, and a decoder chain
+    // ending in Strip(start=1) (EuroLLM) removes it from any decoded string.
+    fakeJsi.registerTokenizer(TOKENIZER_PATH, {
+      tokens: [' Hallo', ' Welt', '.'],
+      concat: true,
+      stripStart: true,
+    });
+    const tokenizer = await loadTokenizer(TOKENIZER_PATH);
+
+    const pieces = stream(tokenizer, [0, 1, 2]);
+
+    expect(pieces).toEqual(['Hallo', ' Welt', '.']);
+    expect(pieces.join('')).toBe(tokenizer.decode(Int32Array.of(0, 1, 2), false));
+    tokenizer.dispose();
+  });
+
+  it('decodes the first tokens on their own', async () => {
+    fakeJsi.registerTokenizer(TOKENIZER_PATH, { tokens: ['Hallo'], concat: true });
+    const tokenizer = await loadTokenizer(TOKENIZER_PATH);
+
+    expect(decodeStreamed(tokenizer, undefined, Int32Array.of(0), false)).toBe('Hallo');
+    tokenizer.dispose();
+  });
+});
diff --git a/packages/react-native-executorch/__tests__/support/fakeJsi.ts b/packages/react-native-executorch/__tests__/support/fakeJsi.ts
index 1c4bc7e5c8..3dbc9062e5 100644
--- a/packages/react-native-executorch/__tests__/support/fakeJsi.ts
+++ b/packages/react-native-executorch/__tests__/support/fakeJsi.ts
@@ -103,6 +103,17 @@ export type FakeVocabulary = {
    * array is mutated in place, which lets a test resolve the ids it was given.
    */
   open?: boolean;
+  /**
+   * Decodes by concatenating token strings, which then carry their own
+   * whitespace, as BPE and SentencePiece vocabularies do. Without it tokens
+   * are words and decode joins them with spaces.
+   */
+  concat?: boolean;
+  /**
+   * Strips one leading space from every decoded string, like a SentencePiece
+   * decoder chain ending in `Strip(start=1)` (e.g. EuroLLM).
+   */
+  stripStart?: boolean;
 };
 
 const vocabularies = new Map<string, FakeVocabulary>();
@@ -147,10 +158,11 @@ function createFakeTokenizer(path: string, vocabulary: FakeVocabulary) {
         return undefined;
       }
     }
-    return ids
+    const text = ids
       .map((id) => vocabulary.tokens[id] ?? '')
       .filter(Boolean)
-      .join(' ');
+      .join(vocabulary.concat ? '' : ' ');
+    return vocabulary.stripStart ? text.replace(/^ /, '') : text;
   };
 
   return {
diff --git a/packages/react-native-executorch/__tests__/support/fakeLLM.ts b/packages/react-native-executorch/__tests__/support/fakeLLM.ts
index cb8471b2ed..0dc4c4b2e1 100644
--- a/packages/react-native-executorch/__tests__/support/fakeLLM.ts
+++ b/packages/react-native-executorch/__tests__/support/fakeLLM.ts
@@ -38,6 +38,8 @@ export type FakeLLMProgram = {
    * the turns it cares about.
    */
   generations?: readonly FakeGeneration[];
+  /** Whether the tokenizer strips a leading space off every decode. */
+  stripStart?: boolean;
 };
 
 /** A prompt the model read: the text of one prefill, and where it started. */
@@ -53,7 +55,7 @@ const VOCAB_SIZE = 4096;
  * @returns Accessors for what the model was asked to read.
  */
 export function registerFakeLLM(modelPath: string, tokenizerPath: string, program: FakeLLMProgram) {
-  const { maxSeqLen = 128, maxContextLen = 1024, eosToken, generations = [] } = program;
+  const { maxSeqLen = 128, maxContextLen = 1024, eosToken, generations = [], stripStart } = program;
 
   const tokens: string[] = [];
   const idOf = (token: string): number => {
@@ -159,7 +161,7 @@ export function registerFakeLLM(modelPath: string, tokenizerPath: string, progra
     },
   });
 
-  fakeJsi.registerTokenizer(tokenizerPath, { tokens, open: true });
+  fakeJsi.registerTokenizer(tokenizerPath, { tokens, open: true, concat: true, stripStart });
 
   return {
     /** @returns Every prompt the model read, prefill by prefill, in order. */
diff --git a/packages/react-native-executorch/__tests__/tasks/llmRunner.test.ts b/packages/react-native-executorch/__tests__/tasks/llmRunner.test.ts
index 0cc1558f17..2013e6941a 100644
--- a/packages/react-native-executorch/__tests__/tasks/llmRunner.test.ts
+++ b/packages/react-native-executorch/__tests__/tasks/llmRunner.test.ts
@@ -540,7 +540,9 @@ describe('createLLMMultimodalRunner — execution & KV cache lifecycle', () => {
 
     expect(stats.numTokens).toBe(3);
     expect(tokens.length).toBe(3);
-    expect(tokens).toEqual(['hello', 'hello', 'hello']);
+    // Each piece is decoded after the previous one, so the pieces add up to
+    // the decode of the whole sequence (this vocabulary joins words with spaces).
+    expect(tokens).toEqual(['hello', ' hello', ' hello']);
   });
 
   it('stops generation early when stop() is called', async () => {
@@ -781,7 +783,9 @@ describe('createLLMGemmaRunner — execution & multimodal prefill', () => {
 
     expect(stats.numTokens).toBe(3);
     expect(tokens.length).toBe(3);
-    expect(tokens).toEqual(['hello', 'hello', 'hello']);
+    // Each piece is decoded after the previous one, so the pieces add up to
+    // the decode of the whole sequence (this vocabulary joins words with spaces).
+    expect(tokens).toEqual(['hello', ' hello', ' hello']);
   });
 
   it('resets KV cache and disposes cleanly', async () => {
diff --git a/packages/react-native-executorch/src/extensions/llm/runners/llmGemmaRunner.ts b/packages/react-native-executorch/src/extensions/llm/runners/llmGemmaRunner.ts
index 77bce0c539..336f806695 100644
--- a/packages/react-native-executorch/src/extensions/llm/runners/llmGemmaRunner.ts
+++ b/packages/react-native-executorch/src/extensions/llm/runners/llmGemmaRunner.ts
@@ -14,6 +14,7 @@ import {
 
 import type { Tokenizer } from '../../nlp';
 import { sample } from '../sampler';
+import { decodeStreamed } from '../utils/streamDecoding';
 
 import type {
   LLMGenerationConfig,
@@ -479,6 +480,8 @@ export function createLLMGemmaRunner(
 
     let numTokens = 0;
     let decodeOffset = 0;
+    // The token group streamed last, decoded as context for the next one.
+    let streamedGroup: Int32Array | undefined;
     let curPos = pos.getBlocking();
 
     try {
@@ -496,9 +499,11 @@ export function createLLMGemmaRunner(
 
         if (onToken) {
           const pendingTokens = Int32Array.from(generatedTokens.slice(decodeOffset));
-          const text = tokenizer.tryDecode(pendingTokens, /* skipSpecialTokens= */ false);
+          // prettier-ignore
+          const text = decodeStreamed(tokenizer, streamedGroup, pendingTokens, /* skipSpecialTokens= */ false);
           if (text !== undefined) {
             decodeOffset = generatedTokens.length;
+            streamedGroup = pendingTokens;
             onToken(text);
           }
         }
diff --git a/packages/react-native-executorch/src/extensions/llm/runners/llmMultimodalRunner.ts b/packages/react-native-executorch/src/extensions/llm/runners/llmMultimodalRunner.ts
index 927fe671ac..130915f120 100644
--- a/packages/react-native-executorch/src/extensions/llm/runners/llmMultimodalRunner.ts
+++ b/packages/react-native-executorch/src/extensions/llm/runners/llmMultimodalRunner.ts
@@ -7,6 +7,7 @@ import { f32, i64, method, validateSpec, DynamicDim as Dyn } from '../../../core
 
 import type { Tokenizer } from '../../nlp';
 import { sample } from '../sampler';
+import { decodeStreamed } from '../utils/streamDecoding';
 
 import type {
   LLMGenerationConfig,
@@ -324,6 +325,8 @@ export function createLLMMultimodalRunner(
 
     let numTokens = 0;
     let decodeOffset = 0;
+    // The token group streamed last, decoded as context for the next one.
+    let streamedGroup: Int32Array | undefined;
     let curPos = pos.getBlocking();
 
     try {
@@ -341,9 +344,11 @@ export function createLLMMultimodalRunner(
 
         if (onToken) {
           const pendingTokens = Int32Array.from(generatedTokens.slice(decodeOffset));
-          const text = tokenizer.tryDecode(pendingTokens, /* skipSpecialTokens= */ true);
+          // prettier-ignore
+          const text = decodeStreamed(tokenizer, streamedGroup, pendingTokens, /* skipSpecialTokens= */ true);
           if (text !== undefined) {
             decodeOffset = generatedTokens.length;
+            streamedGroup = pendingTokens;
             onToken(text);
           }
         }
diff --git a/packages/react-native-executorch/src/extensions/llm/runners/llmTextRunner.ts b/packages/react-native-executorch/src/extensions/llm/runners/llmTextRunner.ts
index a93b9a20a4..a6b25735c6 100644
--- a/packages/react-native-executorch/src/extensions/llm/runners/llmTextRunner.ts
+++ b/packages/react-native-executorch/src/extensions/llm/runners/llmTextRunner.ts
@@ -7,6 +7,7 @@ import { f32, i64, method, DynamicDim as Dyn, validateSpec } from '../../../core
 
 import type { Tokenizer } from '../../nlp';
 import { sample } from '../sampler';
+import { decodeStreamed } from '../utils/streamDecoding';
 
 import type {
   LLMGenerationConfig,
@@ -196,6 +197,8 @@ export function createLLMTextRunner(
 
     let numTokens = 0;
     let decodeOffset = 0;
+    // The token group streamed last, decoded as context for the next one.
+    let streamedGroup: Int32Array | undefined;
     let curPos = pos.getBlocking();
 
     try {
@@ -213,9 +216,11 @@ export function createLLMTextRunner(
 
         if (onToken) {
           const pendingTokens = Int32Array.from(generatedTokens.slice(decodeOffset));
-          const text = tokenizer.tryDecode(pendingTokens, /* skipSpecialTokens= */ false);
+          // prettier-ignore
+          const text = decodeStreamed(tokenizer, streamedGroup, pendingTokens, /* skipSpecialTokens= */ false);
           if (text !== undefined) {
             decodeOffset = generatedTokens.length;
+            streamedGroup = pendingTokens;
             onToken(text);
           }
         }
diff --git a/packages/react-native-executorch/src/extensions/llm/utils/streamDecoding.ts b/packages/react-native-executorch/src/extensions/llm/utils/streamDecoding.ts
new file mode 100644
index 0000000000..0fb8aedb89
--- /dev/null
+++ b/packages/react-native-executorch/src/extensions/llm/utils/streamDecoding.ts
@@ -0,0 +1,45 @@
+/**
+ * Incremental detokenization for streamed LLM generation.
+ */
+
+import type { Tokenizer } from '../../nlp';
+
+/**
+ * Decodes newly generated tokens for streaming, in the context of the tokens
+ * streamed just before them.
+ *
+ * Decoding the new tokens on their own runs the tokenizer's whole decoder
+ * chain on them, so a chain that strips a leading space (SentencePiece-style
+ * `Strip(start=1)`, e.g. EuroLLM) would drop every word break. Decoding them
+ * after the previous group and keeping only what they add matches decoding the
+ * whole sequence at once.
+ * @param tokenizer The model's tokenizer.
+ * @param previous The token group streamed last, or `undefined` at the start.
+ * @param pending The new tokens to decode.
+ * @param skipSpecialTokens Whether to omit special tokens.
+ * @returns The text the pending tokens add, or `undefined` if they end in an
+ * incomplete UTF-8 sequence and more tokens are needed.
+ */
+export function decodeStreamed(
+  tokenizer: Tokenizer,
+  previous: Int32Array | undefined,
+  pending: Int32Array,
+  skipSpecialTokens: boolean
+): string | undefined {
+  'worklet';
+  if (previous === undefined || previous.length === 0) {
+    return tokenizer.tryDecode(pending, skipSpecialTokens);
+  }
+  const prefix = tokenizer.tryDecode(previous, skipSpecialTokens);
+  const joined = new Int32Array(previous.length + pending.length);
+  joined.set(previous);
+  joined.set(pending, previous.length);
+  const text = tokenizer.tryDecode(joined, skipSpecialTokens);
+  if (text === undefined) return undefined;
+  // The previous group decoded on its own before, so a mismatch means the
+  // decoder rewrote its tail; fall back to the pending tokens alone.
+  if (prefix === undefined || !text.startsWith(prefix)) {
+    return tokenizer.tryDecode(pending, skipSpecialTokens);
+  }
+  return text.slice(prefix.length);
+}

From d8551dd27a5630f4c011ae945c8943273c839b9f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mateusz=20S=C5=82uszniak?= <mateusz.sluszniak@swmansion.com>
Date: Wed, 28 Oct 2026 17:43:54 +0100
Subject: [PATCH 4/6] fix(nlp): resolve translation models through VERSION_TAG

---
 packages/react-native-executorch/src/models.ts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/packages/react-native-executorch/src/models.ts b/packages/react-native-executorch/src/models.ts
index b7a857851a..0ffd62bedd 100644
--- a/packages/react-native-executorch/src/models.ts
+++ b/packages/react-native-executorch/src/models.ts
@@ -2156,7 +2156,7 @@ const PPOCRV6_SMALL_VULKAN_FP16: PaddleOcrModel = {
 // =============================================================================
 // Translation
 // =============================================================================
-const OPUS_MT_BASE_URL = `${BASE_URL}/opus-mt-ExecuTorch/${NEXT_VERSION_TAG}`;
+const OPUS_MT_BASE_URL = `${BASE_URL}/opus-mt-ExecuTorch/${VERSION_TAG}`;
 
 const OPUS_MT_EN_DE_XNNPACK_INT8: MarianTranslatorModel = {
   name: 'marian',
@@ -2201,7 +2201,7 @@ const OPUS_MT_FR_EN_XNNPACK_INT8: MarianTranslatorModel = {
   targetLanguage: 'en',
 };
 
-const EUROLLM_BASE_URL = `${BASE_URL}/EuroLLM-1.7B-Instruct-ExecuTorch/${NEXT_VERSION_TAG}/1_7b`;
+const EUROLLM_BASE_URL = `${BASE_URL}/EuroLLM-1.7B-Instruct-ExecuTorch/${VERSION_TAG}/1_7b`;
 
 const EUROLLM_1_7B_XNNPACK_8DA8W: LLMTranslatorModel = {
   name: 'eurollm',

From 7a5ee1c6ed3de5acdad9b9925959b417913d6396 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mateusz=20S=C5=82uszniak?= <mateusz.sluszniak@swmansion.com>
Date: Thu, 29 Oct 2026 17:02:01 +0100
Subject: [PATCH 5/6] feat(nlp): add Hy-MT2-1.8B translation

---
 .cspell-wordlist.txt                          |  1 +
 apps/nlp/app/translation/index.tsx            | 18 +++-
 .../natural-language/07-translation.md        | 35 ++++---
 .../__tests__/tasks/llmTranslation.test.ts    | 59 ++++++++++-
 .../extensions/llm/tasks/llmTranslation.ts    | 97 ++++++++++++++++---
 .../src/hooks/useTranslator.ts                |  5 +-
 .../react-native-executorch/src/models.ts     | 27 ++++++
 7 files changed, 209 insertions(+), 33 deletions(-)

diff --git a/.cspell-wordlist.txt b/.cspell-wordlist.txt
index 56e970131f..0e8d2ace50 100644
--- a/.cspell-wordlist.txt
+++ b/.cspell-wordlist.txt
@@ -447,3 +447,4 @@ grayscale
 Premul
 eurollm
 doclayout
+Uyghur
diff --git a/apps/nlp/app/translation/index.tsx b/apps/nlp/app/translation/index.tsx
index ab34530a0a..6a1e1a4cba 100644
--- a/apps/nlp/app/translation/index.tsx
+++ b/apps/nlp/app/translation/index.tsx
@@ -27,6 +27,8 @@ const SAMPLES: Record<string, string> = {
   es: 'Hoy hace un tiempo precioso. ¿Vamos a dar un paseo por el parque?\nYo llevaré algo de beber.',
   fr: 'Il fait très beau aujourd’hui. On va se promener dans le parc ?\nJ’apporterai quelque chose à boire.',
   pl: 'Dzisiaj jest piękna pogoda. Może pójdziemy na spacer do parku?\nPrzyniosę coś do picia.',
+  zh: '今天天气真好。我们去公园散步好吗？\n我会带点喝的。',
+  ja: '今日はとても良い天気です。公園に散歩に行きませんか？\n飲み物を持っていきます。',
 };
 /* cspell:enable */
 
@@ -36,7 +38,7 @@ const pair = (sourceLanguage: string, targetLanguage: string): Pair => ({
   languages: { sourceLanguage, targetLanguage },
 });
 
-// Opus-MT ships one model per pair; EuroLLM translates every pair with one.
+// Opus-MT ships one model per pair; EuroLLM and Hy-MT2 translate every pair with one.
 const OPUS_MT: { pair: Pair; model: TranslatorModel }[] = [
   { pair: pair('en', 'de'), model: models.translation.OPUS_MT_EN_DE.DEFAULT },
   { pair: pair('de', 'en'), model: models.translation.OPUS_MT_DE_EN.DEFAULT },
@@ -46,6 +48,13 @@ const OPUS_MT: { pair: Pair; model: TranslatorModel }[] = [
   { pair: pair('fr', 'en'), model: models.translation.OPUS_MT_FR_EN.DEFAULT },
 ];
 const EUROLLM_PAIRS = [...OPUS_MT.map((m) => m.pair), pair('en', 'pl'), pair('pl', 'en')];
+const HY_MT2_PAIRS = [
+  ...EUROLLM_PAIRS,
+  pair('en', 'zh'),
+  pair('zh', 'en'),
+  pair('en', 'ja'),
+  pair('ja', 'en'),
+];
 
 const FAMILIES = [
   {
@@ -62,6 +71,13 @@ const FAMILIES = [
     pairs: EUROLLM_PAIRS,
     modelFor: () => models.translation.EUROLLM_1_7B.DEFAULT as TranslatorModel,
   },
+  {
+    label: 'Hy-MT2',
+    description:
+      'One 1.2 GB model for 38 languages and dialects, strongest on Chinese. Translates a line at a time.',
+    pairs: HY_MT2_PAIRS,
+    modelFor: () => models.translation.HY_MT2_1_8B.DEFAULT as TranslatorModel,
+  },
 ];
 
 function TranslationContent() {
diff --git a/docs/docs/02-extensions/natural-language/07-translation.md b/docs/docs/02-extensions/natural-language/07-translation.md
index 65b4e828ef..91ceaf4b9f 100644
--- a/docs/docs/02-extensions/natural-language/07-translation.md
+++ b/docs/docs/02-extensions/natural-language/07-translation.md
@@ -1,7 +1,7 @@
 ---
 title: Translation
 slug: /extensions/translation
-description: 'Translate text between languages fully on-device in React Native with Opus-MT and EuroLLM models.'
+description: 'Translate text between languages fully on-device in React Native with Opus-MT, EuroLLM and Hy-MT2 models.'
 keywords:
   [
     react native,
@@ -10,6 +10,7 @@ keywords:
     opus-mt,
     marian,
     eurollm,
+    hy-mt2,
     mobile ml,
     on-device ai,
   ]
@@ -21,6 +22,7 @@ Translation models turn text in one language into another without sending it off
 
 - [Opus-MT](https://github.com/Helsinki-NLP/Opus-MT): small (~110 MB) and fast, one model per language pair, such as English to German.
 - [EuroLLM-1.7B-Instruct](https://huggingface.co/utter-project/EuroLLM-1.7B-Instruct): one 1.7 GB model that translates between any two of its 35 languages.
+- [Hy-MT2-1.8B](https://huggingface.co/tencent/Hy-MT2-1.8B): one 1.2 GB model that translates between any two of its 38 languages and dialects, and is stronger than EuroLLM on Chinese.
 
 ## Quick Start
 
@@ -46,7 +48,7 @@ function MyComponent() {
 }
 ```
 
-An Opus-MT model accepts only its own pair. With `models.translation.EUROLLM_1_7B.DEFAULT`, the pair can change on every call without reloading the model.
+An Opus-MT model accepts only its own pair. With `models.translation.EUROLLM_1_7B.DEFAULT` or `models.translation.HY_MT2_1_8B.DEFAULT`, the pair can change on every call without reloading the model.
 
 ## Streaming
 
@@ -67,10 +69,12 @@ Call [`translateStop()`](../../06-api-reference/type-aliases/Translator.md#trans
 Line breaks are kept in the output for both kinds of model.
 
 - **Opus-MT** models are trained on single sentences, so the input is split after sentence-ending punctuation (`.`, `!`, `?`) and at line breaks, and each sentence is translated on its own. A single sentence longer than the model's maximum source length (256 tokens) is truncated, and one sentence translates to at most 256 tokens.
-- **EuroLLM** translates each line on its own with the model card's prompt, decoding greedily. A line and its translation together must fit the 1024-token context.
+- **EuroLLM** and **Hy-MT2** translate each line on their own with the model card's prompt, decoding greedily. A line and its translation together must fit the 1024-token context.
 
 EuroLLM supports Arabic (`ar`), Bulgarian (`bg`), Catalan (`ca`), Chinese (`zh`), Croatian (`hr`), Czech (`cs`), Danish (`da`), Dutch (`nl`), English (`en`), Estonian (`et`), Finnish (`fi`), French (`fr`), Galician (`gl`), German (`de`), Greek (`el`), Hindi (`hi`), Hungarian (`hu`), Irish (`ga`), Italian (`it`), Japanese (`ja`), Korean (`ko`), Latvian (`lv`), Lithuanian (`lt`), Maltese (`mt`), Norwegian (`no`), Polish (`pl`), Portuguese (`pt`), Romanian (`ro`), Russian (`ru`), Slovak (`sk`), Slovenian (`sl`), Spanish (`es`), Swedish (`sv`), Turkish (`tr`) and Ukrainian (`uk`).
 
+Hy-MT2 supports Arabic (`ar`), Bengali (`bn`), Burmese (`my`), Cantonese (`yue`), Chinese (`zh`), Traditional Chinese (`zh-Hant`), Czech (`cs`), Dutch (`nl`), English (`en`), Filipino (`tl`), French (`fr`), German (`de`), Gujarati (`gu`), Hebrew (`he`), Hindi (`hi`), Indonesian (`id`), Italian (`it`), Japanese (`ja`), Kazakh (`kk`), Khmer (`km`), Korean (`ko`), Malay (`ms`), Marathi (`mr`), Mongolian (`mn`), Persian (`fa`), Polish (`pl`), Portuguese (`pt`), Russian (`ru`), Spanish (`es`), Tamil (`ta`), Telugu (`te`), Thai (`th`), Tibetan (`bo`), Turkish (`tr`), Ukrainian (`uk`), Urdu (`ur`), Uyghur (`ug`) and Vietnamese (`vi`).
+
 ## Imperative API
 
 For use outside React components, create the pipeline with [`createMarianTranslator`](../../06-api-reference/functions/createMarianTranslator.md) or [`createLLMTranslator`](../../06-api-reference/functions/createLLMTranslator.md):
@@ -99,18 +103,19 @@ try {
 
 The models are available in [`models.translation`](../../06-api-reference/variables/models.md#translation):
 
-| Model           | Direction               | Size   | Supported Backends            |
-| :-------------- | :---------------------- | :----- | :---------------------------- |
-| `OPUS_MT_EN_DE` | English → German        | 107 MB | XNNPACK (CPU)                 |
-| `OPUS_MT_DE_EN` | German → English        | 107 MB | XNNPACK (CPU)                 |
-| `OPUS_MT_EN_ES` | English → Spanish       | 114 MB | XNNPACK (CPU)                 |
-| `OPUS_MT_ES_EN` | Spanish → English       | 114 MB | XNNPACK (CPU)                 |
-| `OPUS_MT_EN_FR` | English → French        | 108 MB | XNNPACK (CPU)                 |
-| `OPUS_MT_FR_EN` | French → English        | 108 MB | XNNPACK (CPU)                 |
-| `EUROLLM_1_7B`  | Any of its 35 languages | 1.7 GB | XNNPACK (CPU), MLX (iOS, GPU) |
+| Model           | Direction               | Size                | Supported Backends            |
+| :-------------- | :---------------------- | :------------------ | :---------------------------- |
+| `OPUS_MT_EN_DE` | English → German        | 107 MB              | XNNPACK (CPU)                 |
+| `OPUS_MT_DE_EN` | German → English        | 107 MB              | XNNPACK (CPU)                 |
+| `OPUS_MT_EN_ES` | English → Spanish       | 114 MB              | XNNPACK (CPU)                 |
+| `OPUS_MT_ES_EN` | Spanish → English       | 114 MB              | XNNPACK (CPU)                 |
+| `OPUS_MT_EN_FR` | English → French        | 108 MB              | XNNPACK (CPU)                 |
+| `OPUS_MT_FR_EN` | French → English        | 108 MB              | XNNPACK (CPU)                 |
+| `EUROLLM_1_7B`  | Any of its 35 languages | 1.7 GB              | XNNPACK (CPU), MLX (iOS, GPU) |
+| `HY_MT2_1_8B`   | Any of its 38 languages | 1.2 GB (MLX 1.8 GB) | XNNPACK (CPU), MLX (iOS, GPU) |
 
 :::info License
-`OPUS_MT_EN_DE` is licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/) and requires attribution to the [Helsinki-NLP Opus-MT](https://huggingface.co/Helsinki-NLP/opus-mt-en-de) project. The other Opus-MT pairs and EuroLLM are Apache-2.0.
+`OPUS_MT_EN_DE` is licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/) and requires attribution to the [Helsinki-NLP Opus-MT](https://huggingface.co/Helsinki-NLP/opus-mt-en-de) project. The other Opus-MT pairs, EuroLLM and Hy-MT2 are Apache-2.0.
 :::
 
 ## API Reference
@@ -119,7 +124,7 @@ The models are available in [`models.translation`](../../06-api-reference/variab
 
 - [`useTranslator()`](../../06-api-reference/functions/useTranslator.md) — React hook for translation model downloading, state, and lifecycle.
 - [`createMarianTranslator()`](../../06-api-reference/functions/createMarianTranslator.md) — Imperative factory for Opus-MT translation pipelines.
-- [`createLLMTranslator()`](../../06-api-reference/functions/createLLMTranslator.md) — Imperative factory for EuroLLM translation pipelines.
+- [`createLLMTranslator()`](../../06-api-reference/functions/createLLMTranslator.md) — Imperative factory for EuroLLM and Hy-MT2 translation pipelines.
 
 ### Types
 
@@ -128,7 +133,7 @@ The models are available in [`models.translation`](../../06-api-reference/variab
 - [`TranslatorModel`](../../06-api-reference/type-aliases/TranslatorModel.md) — Any translation model configuration.
 - [`MarianTranslator`](../../06-api-reference/type-aliases/MarianTranslator.md) — Opus-MT runner, which adds [`translateWorklet`](../../06-api-reference/type-aliases/MarianTranslator.md#translateworklet).
 - [`MarianTranslatorModel`](../../06-api-reference/type-aliases/MarianTranslatorModel.md) — Opus-MT configuration with model path, tokenizer path, and language pair.
-- [`LLMTranslatorModel`](../../06-api-reference/type-aliases/LLMTranslatorModel.md) — EuroLLM configuration with model, tokenizer, and tokenizer config paths.
+- [`LLMTranslatorModel`](../../06-api-reference/type-aliases/LLMTranslatorModel.md) — EuroLLM or Hy-MT2 configuration with model, tokenizer, and tokenizer config paths.
 
 ### Model Presets
 
diff --git a/packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts b/packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts
index e6e5a185e2..5b18584f9d 100644
--- a/packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts
+++ b/packages/react-native-executorch/__tests__/tasks/llmTranslation.test.ts
@@ -1,5 +1,5 @@
 /**
- * The LLM (EuroLLM) translator.
+ * The LLM (EuroLLM, Hy-MT2) translator.
  *
  * It runs on the real chat session and LLM runner; only the `.pte` below them
  * is scripted (see `support/fakeLLM.ts`), so a test sees the exact prompt each
@@ -121,3 +121,60 @@ describe('createLLMTranslator', () => {
     expect(fakeJsi.liveTokenizers()).toEqual([]);
   });
 });
+
+describe('createLLMTranslator with Hy-MT2', () => {
+  const HY_EOS = '<｜hy_place▁holder▁no▁2｜>';
+  // Hy-MT2-1.8B's chat_template.jinja, which the published tokenizer_config.json carries.
+  const HY_CHAT_TEMPLATE =
+    "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}<｜hy_begin▁of▁sentence｜>{{ system_message }}<｜hy_place▁holder▁no▁3｜>{% else %}{% set loop_messages = messages %}<｜hy_begin▁of▁sentence｜>{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}<｜hy_User｜>{{ message['content'] }}{% elif message['role'] == 'assistant' %}<｜hy_Assistant｜>{{ message['content'] }}<｜hy_place▁holder▁no▁2｜>{% endif %}{% endfor %}{% if add_generation_prompt %}<｜hy_Assistant｜>{% else %}<｜hy_place▁holder▁no▁8｜>{% endif %}";
+  const hyConfig = { ...config, name: 'hy-mt2' as const };
+  const hyTurn = (content: string) =>
+    squash(`<｜hy_begin▁of▁sentence｜><｜hy_User｜>${content}<｜hy_Assistant｜>`);
+
+  beforeEach(() => {
+    // The fake fs stores one byte per char, so anything outside printable ASCII
+    // goes in as a JSON escape.
+    /* eslint-disable camelcase */
+    const json = JSON.stringify({ chat_template: HY_CHAT_TEMPLATE, eos_token: HY_EOS });
+    /* eslint-enable camelcase */
+    fakeFs.write(
+      TOKENIZER_CONFIG_PATH,
+      json.replace(/[^ -~]/g, (c) => `\\u${c.charCodeAt(0).toString(16).padStart(4, '0')}`)
+    );
+    llm = registerFakeLLM(MODEL_PATH, TOKENIZER_PATH, {
+      eosToken: HY_EOS,
+      generations: [{ response: 'Hallo Welt.' }],
+    });
+  });
+
+  it('sends the model card prompt naming the target language', async () => {
+    const translator = tracked(await createLLMTranslator(hyConfig));
+
+    expect(await translator.translate('Hello world.', EN_DE)).toBe('Hallo Welt.');
+    expect(promptsSent()).toEqual([
+      hyTurn(
+        'Translate the following text into German. Note that you should only output ' +
+          'the translated result without any additional explanation:\n\nHello world.'
+      ),
+    ]);
+  });
+
+  it('uses the Chinese prompt when either side is Chinese', async () => {
+    const translator = tracked(await createLLMTranslator(hyConfig));
+
+    await translator.translate('Hello world.', { sourceLanguage: 'en', targetLanguage: 'zh' });
+
+    expect(promptsSent()).toEqual([
+      hyTurn('将以下文本翻译为中文，注意只需要输出翻译后的结果，不要额外解释：\n\nHello world.'),
+    ]);
+  });
+
+  it('rejects a language the model does not know', async () => {
+    const translator = tracked(await createLLMTranslator(hyConfig));
+
+    // Maltese is a EuroLLM language, not a Hy-MT2 one.
+    await expect(
+      translator.translate('Hello', { sourceLanguage: 'mt', targetLanguage: 'en' })
+    ).rejects.toThrow(/unsupported language 'mt'/);
+  });
+});
diff --git a/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts b/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts
index bd1761431c..5c8230fe66 100644
--- a/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts
+++ b/packages/react-native-executorch/src/extensions/llm/tasks/llmTranslation.ts
@@ -1,5 +1,5 @@
 /**
- * Instruction-tuned LLM (EuroLLM) machine translation task pipeline.
+ * Instruction-tuned LLM (EuroLLM, Hy-MT2) machine translation task pipeline.
  */
 
 import { scheduleOnRN, type WorkletRuntime } from 'react-native-worklets';
@@ -59,6 +59,51 @@ const EUROLLM_LANGUAGES: Readonly<Record<string, string>> = {
   zh: 'Chinese',
 };
 
+// Languages Hy-MT2 was trained on, keyed by ISO 639 code, with the English
+// and Chinese names its model card prompts use.
+const HY_MT2_LANGUAGES: Readonly<Record<string, readonly [english: string, chinese: string]>> = {
+  'ar': ['Arabic', '阿拉伯语'],
+  'bn': ['Bengali', '孟加拉语'],
+  'bo': ['Tibetan', '藏语'],
+  'cs': ['Czech', '捷克语'],
+  'de': ['German', '德语'],
+  'en': ['English', '英语'],
+  'es': ['Spanish', '西班牙语'],
+  'fa': ['Persian', '波斯语'],
+  'fr': ['French', '法语'],
+  'gu': ['Gujarati', '古吉拉特语'],
+  'he': ['Hebrew', '希伯来语'],
+  'hi': ['Hindi', '印地语'],
+  'id': ['Indonesian', '印尼语'],
+  'it': ['Italian', '意大利语'],
+  'ja': ['Japanese', '日语'],
+  'kk': ['Kazakh', '哈萨克语'],
+  'km': ['Khmer', '高棉语'],
+  'ko': ['Korean', '韩语'],
+  'mn': ['Mongolian', '蒙古语'],
+  'mr': ['Marathi', '马拉地语'],
+  'ms': ['Malay', '马来语'],
+  'my': ['Burmese', '缅甸语'],
+  'nl': ['Dutch', '荷兰语'],
+  'pl': ['Polish', '波兰语'],
+  'pt': ['Portuguese', '葡萄牙语'],
+  'ru': ['Russian', '俄语'],
+  'ta': ['Tamil', '泰米尔语'],
+  'te': ['Telugu', '泰卢固语'],
+  'th': ['Thai', '泰语'],
+  'tl': ['Filipino', '菲律宾语'],
+  'tr': ['Turkish', '土耳其语'],
+  'ug': ['Uyghur', '维吾尔语'],
+  'uk': ['Ukrainian', '乌克兰语'],
+  'ur': ['Urdu', '乌尔都语'],
+  'vi': ['Vietnamese', '越南语'],
+  'yue': ['Cantonese', '粤语'],
+  'zh': ['Chinese', '中文'],
+  'zh-Hant': ['Traditional Chinese', '繁体中文'],
+};
+
+const HY_MT2_CHINESE = new Set(['zh', 'zh-Hant', 'yue']);
+
 /**
  * Paths required to instantiate an LLM translator. One model translates
  * between any two of its supported languages.
@@ -66,15 +111,37 @@ const EUROLLM_LANGUAGES: Readonly<Record<string, string>> = {
  */
 export type LLMTranslatorModel = LLMModel & {
   /** Identifies the pipeline this config belongs to. */
-  readonly name: 'eurollm';
+  readonly name: 'eurollm' | 'hy-mt2';
 };
 
-const languageName = (code: string): string => {
-  const name = EUROLLM_LANGUAGES[code];
-  if (!name) {
-    throw RnExecuTorchError('INVALID_ARGUMENT', `translate: unsupported language '${code}'.`);
-  }
-  return name;
+const unsupported = (code: string) =>
+  RnExecuTorchError('INVALID_ARGUMENT', `translate: unsupported language '${code}'.`);
+
+// The user turn each model card prompts a translation with. Throws for a
+// language the model does not know.
+const PROMPTS: Readonly<
+  Record<LLMTranslatorModel['name'], (line: string, source: string, target: string) => string>
+> = {
+  'eurollm': (line, source, target) => {
+    const src = EUROLLM_LANGUAGES[source];
+    const tgt = EUROLLM_LANGUAGES[target];
+    if (!src) throw unsupported(source);
+    if (!tgt) throw unsupported(target);
+    return `Translate the following ${src} source text to ${tgt}:\n${src}: ${line} \n${tgt}: `;
+  },
+  // The card names only the target. Pairs with Chinese take its Chinese prompt.
+  'hy-mt2': (line, source, target) => {
+    const tgt = HY_MT2_LANGUAGES[target];
+    if (!HY_MT2_LANGUAGES[source]) throw unsupported(source);
+    if (!tgt) throw unsupported(target);
+    if (HY_MT2_CHINESE.has(source) || HY_MT2_CHINESE.has(target)) {
+      return `将以下文本翻译为${tgt[1]}，注意只需要输出翻译后的结果，不要额外解释：\n\n${line}`;
+    }
+    return (
+      `Translate the following text into ${tgt[0]}. Note that you should only output ` +
+      `the translated result without any additional explanation:\n\n${line}`
+    );
+  },
 };
 
 function generateWorklet(
@@ -98,7 +165,8 @@ function generateWorklet(
 const GENERATION_CONFIG: LLMGenerationConfig = { temperature: 0 };
 
 /**
- * Creates a translator on top of an instruction-tuned LLM such as EuroLLM.
+ * Creates a translator on top of an instruction-tuned LLM such as EuroLLM or
+ * Hy-MT2.
  *
  * Every line is sent as its own single-turn chat with the model card's
  * translation prompt, from an empty KV cache, and decoded greedily. One model
@@ -137,15 +205,15 @@ export async function createLLMTranslator(
     let busy = false;
     let stopped = false;
 
+    const userTurn = PROMPTS[config.name];
+
     const translateLine = async (
       line: string,
       source: string,
       target: string,
       onPiece: (piece: string) => void
     ): Promise<string> => {
-      const content =
-        `Translate the following ${source} source text to ${target}:\n` +
-        `${source}: ${line} \n${target}: `;
+      const content = userTurn(line, source, target);
       runner.reset();
       const prompt = chatPreprocessor.process([{ role: 'user', content }], 1, {
         addGenPrompt: true,
@@ -169,8 +237,9 @@ export async function createLLMTranslator(
       languages: TranslationLanguages,
       onToken?: (token: string) => void
     ): Promise<string> => {
-      const source = languageName(languages.sourceLanguage);
-      const target = languageName(languages.targetLanguage);
+      const { sourceLanguage: source, targetLanguage: target } = languages;
+      // Validates the pair before anything is queued.
+      userTurn('', source, target);
       if (busy) {
         throw RnExecuTorchError('RESOURCE_BUSY', 'translate: A translation is in progress.');
       }
diff --git a/packages/react-native-executorch/src/hooks/useTranslator.ts b/packages/react-native-executorch/src/hooks/useTranslator.ts
index eac9fc9732..d5a6872ed2 100644
--- a/packages/react-native-executorch/src/hooks/useTranslator.ts
+++ b/packages/react-native-executorch/src/hooks/useTranslator.ts
@@ -18,8 +18,8 @@ export type TranslatorModel = MarianTranslatorModel | LLMTranslatorModel;
 
 /**
  * React hook to load and run a translation pipeline: Marian (Opus-MT), one
- * model per language pair, or an LLM (EuroLLM) that translates between any two
- * of its languages.
+ * model per language pair, or an LLM (EuroLLM, Hy-MT2) that translates between
+ * any two of its languages.
  *
  * This hook manages downloading (if remote URLs are provided) and loading the
  * model and tokenizer, tracking download progress and load errors, and
@@ -60,6 +60,7 @@ export function useTranslator<C extends TranslatorModel>(
       case 'marian':
         return createMarianTranslator(translatorConfig);
       case 'eurollm':
+      case 'hy-mt2':
         return createLLMTranslator(translatorConfig);
     }
   };
diff --git a/packages/react-native-executorch/src/models.ts b/packages/react-native-executorch/src/models.ts
index 0ffd62bedd..b9f8aad82a 100644
--- a/packages/react-native-executorch/src/models.ts
+++ b/packages/react-native-executorch/src/models.ts
@@ -2216,6 +2216,27 @@ const EUROLLM_1_7B_MLX_INT8: LLMTranslatorModel = {
   tokenizerConfigPath: `${EUROLLM_BASE_URL}/tokenizer_config.json`,
 };
 
+const HY_MT2_BASE_URL = `${BASE_URL}/Hy-MT2-1.8B-ExecuTorch/${VERSION_TAG}/1_8b`;
+
+const HY_MT2_1_8B_XNNPACK_8DA4W: LLMTranslatorModel = {
+  name: 'hy-mt2',
+  modelPath: `${HY_MT2_BASE_URL}/xnnpack/hy_mt2_1_8b_xnnpack_8da4w.pte`,
+  tokenizerPath: `${HY_MT2_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${HY_MT2_BASE_URL}/tokenizer_config.json`,
+};
+const HY_MT2_1_8B_XNNPACK_8DA8W: LLMTranslatorModel = {
+  name: 'hy-mt2',
+  modelPath: `${HY_MT2_BASE_URL}/xnnpack/hy_mt2_1_8b_xnnpack_8da8w.pte`,
+  tokenizerPath: `${HY_MT2_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${HY_MT2_BASE_URL}/tokenizer_config.json`,
+};
+const HY_MT2_1_8B_MLX_INT8: LLMTranslatorModel = {
+  name: 'hy-mt2',
+  modelPath: `${HY_MT2_BASE_URL}/mlx/hy_mt2_1_8b_mlx_int8.pte`,
+  tokenizerPath: `${HY_MT2_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${HY_MT2_BASE_URL}/tokenizer_config.json`,
+};
+
 // =============================================================================
 // LLMs
 // =============================================================================
@@ -3806,6 +3827,12 @@ export const models = {
       XNNPACK_8DA8W: EUROLLM_1_7B_XNNPACK_8DA8W,
       MLX_INT8: EUROLLM_1_7B_MLX_INT8,
     }),
+    /** Hy-MT2 1.8B: any two of its 38 languages and dialects with one model. */
+    HY_MT2_1_8B: variants({
+      XNNPACK_8DA4W: HY_MT2_1_8B_XNNPACK_8DA4W,
+      XNNPACK_8DA8W: HY_MT2_1_8B_XNNPACK_8DA8W,
+      MLX_INT8: HY_MT2_1_8B_MLX_INT8,
+    }),
   },
 
   /**

From d0026cd1d7a94f290f38124050c434d235c4e819 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mateusz=20S=C5=82uszniak?= <mateusz.sluszniak@swmansion.com>
Date: Fri, 30 Oct 2026 14:58:55 +0100
Subject: [PATCH 6/6] feat(nlp): add Hy-MT2 MLX int4 variant

---
 packages/react-native-executorch/src/models.ts | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/packages/react-native-executorch/src/models.ts b/packages/react-native-executorch/src/models.ts
index 7327a5598e..7b2db003f3 100644
--- a/packages/react-native-executorch/src/models.ts
+++ b/packages/react-native-executorch/src/models.ts
@@ -2263,6 +2263,12 @@ const HY_MT2_1_8B_MLX_INT8: LLMTranslatorModel = {
   tokenizerPath: `${HY_MT2_BASE_URL}/tokenizer.json`,
   tokenizerConfigPath: `${HY_MT2_BASE_URL}/tokenizer_config.json`,
 };
+const HY_MT2_1_8B_MLX_INT4: LLMTranslatorModel = {
+  name: 'hy-mt2',
+  modelPath: `${HY_MT2_BASE_URL}/mlx/hy_mt2_1_8b_mlx_int4.pte`,
+  tokenizerPath: `${HY_MT2_BASE_URL}/tokenizer.json`,
+  tokenizerConfigPath: `${HY_MT2_BASE_URL}/tokenizer_config.json`,
+};
 
 // =============================================================================
 // LLMs
@@ -3982,6 +3988,7 @@ export const models = {
       XNNPACK_8DA4W: HY_MT2_1_8B_XNNPACK_8DA4W,
       XNNPACK_8DA8W: HY_MT2_1_8B_XNNPACK_8DA8W,
       MLX_INT8: HY_MT2_1_8B_MLX_INT8,
+      MLX_INT4: HY_MT2_1_8B_MLX_INT4,
     }),
   },