@@ -29,7 +29,7 @@ body:
         - Dense decoder-only (e.g. Llama, Qwen, Gemma, Mistral, Nemotron)
         - MoE decoder-only (e.g. DeepSeek V3, OLMoE, Qwen3-MoE, MiniMax-M2)
         - VLM / multimodal (e.g. Qwen-VL, Gemma-VL, Nemotron-VL)
-        - SSM / hybrid (e.g. Mamba, Nemotron-H)
+        - SSM / hybrid (e.g. Mamba, Nemotron 3)
         - Encoder-decoder (e.g. T5)
         - Other / unsure
     validations:
 
@@ -221,8 +221,6 @@ For a deeper dive into conversion design and advanced usage, see the [models REA
 
 Megatron Bridge provides out-of-the-box bridges and training recipes for a wide range of models, built on top of base model architectures from [Megatron Core](https://github.com/NVIDIA/Megatron-LM/tree/main/megatron/core). Refer to the [models directory](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/src/megatron/bridge/models) for the full list of model bridges.
 
-> **Deprecation notice:** Nemotron H v1 (4B/8B/47B/56B) is no longer actively maintained and will be removed in Megatron Bridge 0.7.0.
-
 | Family | Supported variants |
 |----------------|--------------------|
 | [**BAGEL**](docs/models/bagel/bagel.md) | BAGEL-7B-MoT (requires the tested MCore `dev` revision and `bagel` extra) |
@@ -244,7 +242,7 @@ Megatron Bridge provides out-of-the-box bridges and training recipes for a wide
 | [**Xiaomi-MiMo**](docs/models/mimo/index.md) | Xiaomi-MiMo, MiMo-V2-Flash |
 | [**Moonlight**](docs/models/moonlight/index.md) | Moonlight |
 | [**Muse Glimmer**](docs/models/muse_glimmer/muse-glimmer.md) | Muse Glimmer 30B |
-| [**Nemotron**](docs/models/nemotron/index.md) | Nemotron H v1 (deprecated), Nemotron-3 Nano, Nemotron-3 Super, Nemotron-3 Ultra, Nemotron-3 Nano Omni |
+| [**Nemotron**](docs/models/nemotron/index.md) | Nemotron-3 Nano, Nemotron-3 Super, Nemotron-3 Ultra, Nemotron-3 Nano Omni |
 | [**OLMoE**](docs/models/olmoe/index.md) | OLMoE |
 | [**Qwen**](docs/models/qwen/index.md) | Qwen2 / Qwen2.5, Qwen3, Qwen3-MoE, Qwen3 Next, Qwen3.5 (dense/MoE), Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL, Qwen2 Audio, Qwen2.5-Omni, Qwen3-Omni, Qwen3-ASR |
 | [**Sarvam**](docs/models/sarvam/index.md) | Sarvam |
 
@@ -36,7 +36,6 @@
 "./versions/nightly/pages/models/kimi/kimi-k25-vl.mdx": 2
 "./versions/nightly/pages/models/llama/llama3.mdx": 2
 "./versions/nightly/pages/models/mistral/ministral3.mdx": 2
-"./versions/nightly/pages/models/nemotron/nemotronh.mdx": 2
 "./versions/nightly/pages/models/qwen/qwen3-moe.mdx": 4
 "./versions/nightly/pages/performance-guide.mdx": 2
 "./versions/nightly/pages/performance-summary-archive.mdx": 2
 
@@ -112,8 +112,6 @@ navigation:
       path: ./nightly/pages/models/moonlight/moonlight.mdx
     section: Moonlight
   - contents:
-    - page: Nemotron H
-      path: ./nightly/pages/models/nemotron/nemotronh.mdx
     - page: Nemotron 3 Nano 30B-A3B
       path: ./nightly/pages/models/nemotron/nemotron3-nano.mdx
     - page: Nemotron 3 Nano 4B
 
@@ -217,7 +217,7 @@ Megatron Bridge provides out-of-the-box bridges and training recipes for a wide
 | [**Mistral**](docs/models/mistral/index.md) | Ministral 3 (3B/8B/14B) |
 | [**Xiaomi-MiMo**](docs/models/mimo/index.md) | Xiaomi-MiMo |
 | [**Moonlight**](docs/models/moonlight/index.md) | Moonlight |
-| [**Nemotron**](docs/models/nemotron/index.md) | Nemotron H, Nemotron-3 Nano, Nemotron-3 Super, Nemotron-3 Nano Omni |
+| [**Nemotron**](docs/models/nemotron/index.md) | Nemotron-3 Nano, Nemotron-3 Super, Nemotron-3 Nano Omni |
 | [**OLMoE**](docs/models/olmoe/index.md) | OLMoE |
 | [**Qwen**](docs/models/qwen/index.md) | Qwen2 / Qwen2.5, Qwen3, Qwen3-MoE, Qwen3 Next, Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL, Qwen2 Audio, Qwen2.5-Omni, Qwen3-Omni, Qwen3-ASR |
 | [**Sarvam**](docs/models/sarvam/index.md) | Sarvam |
 
@@ -188,7 +188,6 @@ and ModelOpt scale suffixes, so a pattern can target the logical parameter name
 | Llama-3.2-1B | ✅ | ✅ |
 | Qwen3-8B | ✅ | ✅ |
 | Qwen3-30B-A3B | ✅ | ✅ |
-| Nemotron-H-8B-Base-8K | ✅ | ✅ |
 | Qwen3-VL-8B-Instruct | ✅ | ✅ |
 | Qwen3-VL-30B-A3B-Instruct | ✅ | ✅ |
 
 
@@ -4,7 +4,6 @@ Nemotron model documentation is organized by model variant.
 
 | Variant | Guide |
 |---------|-------|
-| Nemotron H | [nemotronh.md](nemotronh.md) |
 | Nemotron-3 Nano 30B-A3B | [nemotron3-nano.md](nemotron3-nano.md) |
 | Nemotron-3 Nano 4B | [nemotron3-nano-4b.md](nemotron3-nano-4b.md) |
 | Nemotron-3 Super | [nemotron3-super.md](nemotron3-super.md) |
 
@@ -1,313 +1,7 @@
-# Nemotron H
+# Nemotron H v1 support removed
 
-> **Deprecation notice:** Nemotron H v1 support (4B, 8B, 47B, and 56B) is no longer actively maintained or tested against current upstream checkpoints and will be removed in Megatron Bridge 0.7.0. Nemotron 3 is not deprecated.
+{/* Keep this notice for previews that use navigation from main. */}
 
-[Nemotron H](https://huggingface.co/collections/nvidia/nemotron-h) is a family of hybrid SSM-Attention models combining Mamba and attention layers.
+Support for Nemotron H v1 (4B, 8B, 47B, and 56B) has been removed from Megatron Bridge. The former conversion and training instructions no longer apply.
 
-The Nemotron H family includes models from 4B to 56B parameters with 8K context length.
-
-## Model Families
-
-### Nemotron H
-- **4B**: 52 layers, 3072 hidden size, 8K context
-- **8B**: 52 layers, 4096 hidden size, 8K context  
-- **47B**: 98 layers, 8192 hidden size, 8K context
-- **56B**: 118 layers, 8192 hidden size, 8K context
-
-## Model Architecture
-
-### Common Features Across All Models
-- **Architecture**: Hybrid SSM-Attention (Mamba + Multi-Query Attention)
-- **SSM**: Mamba-2 selective state space layers
-- **Attention**: Multi-query attention with QK LayerNorm and RoPE
-- **Activation**: Squared ReLU (SwiGLU in FFN)
-- **Normalization**: RMSNorm
-- **Position Embedding**: RoPE (Rotary Position Embeddings)
-- **Hybrid Pattern**: Configurable layer-wise mixing of Mamba ("M") and Attention ("*") layers
-
-### Nemotron H 4B Specifications
-- **Parameters**: 4B
-- **Layers**: 52 (Hybrid pattern: `M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M-`)
-- **Hidden size**: 3072
-- **FFN hidden size**: 12288
-- **Attention heads**: 32 query heads, 8 key-value groups
-- **KV channels**: 128
-- **Mamba heads**: 112
-- **Mamba head dim**: 64
-- **Mamba state dim**: 128
-- **Context Length**: 8K tokens
-
-### Nemotron H 8B Specifications
-- **Parameters**: 8B
-- **Layers**: 52 (Hybrid pattern: `M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M-`)
-- **Hidden size**: 4096
-- **FFN hidden size**: 21504
-- **Attention heads**: 32 query heads, 8 key-value groups
-- **KV channels**: 128
-- **Mamba heads**: 128
-- **Mamba head dim**: 64
-- **Mamba state dim**: 128
-- **Context Length**: 8K tokens
-
-### Nemotron H 47B Specifications
-- **Parameters**: 47B
-- **Layers**: 98
-- **Hidden size**: 8192
-- **FFN hidden size**: 30720
-- **Attention heads**: 64 query heads, 8 key-value groups
-- **KV channels**: 128
-- **Mamba heads**: 256
-- **Mamba head dim**: 64
-- **Mamba state dim**: 256
-- **Context Length**: 8K tokens
-
-### Nemotron H 56B Specifications
-- **Parameters**: 56B
-- **Layers**: 118
-- **Hidden size**: 8192
-- **FFN hidden size**: 32768
-- **Attention heads**: 64 query heads, 8 key-value groups
-- **KV channels**: 128
-- **Mamba heads**: 256
-- **Mamba head dim**: 64
-- **Mamba state dim**: 256
-- **Context Length**: 8K tokens
-
-## Key Features
-
-### Hybrid SSM-Attention Architecture
-- **Mamba Layers (M)**: State space model layers for efficient long-range modeling
-- **Attention Layers (*)**: Standard multi-query attention for complex reasoning
-- **Configurable Pattern**: Each model has a predefined hybrid pattern balancing efficiency and performance
-
-### Advanced Optimizations
-- **Squared ReLU Activation**: Enhanced non-linearity for better gradient flow
-- **QK LayerNorm**: Applies LayerNorm to query and key projections for training stability
-- **RoPE**: Rotary Position Embeddings with base 10000
-- **Multi-Query Attention**: Efficient attention with shared key-value heads
-- **Selective State Space**: Mamba-2 architecture with selective gating
-
-## Conversion with 🤗 Hugging Face
-
-### Load HF → Megatron
-
-#### Nemotron H Models
-```python
-from megatron.bridge import AutoBridge
-
-# Example: Nemotron H 8B
-bridge = AutoBridge.from_hf_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
-provider = bridge.to_megatron_provider()
-
-# Configure parallelism before instantiating the model
-provider.tensor_model_parallel_size = 2
-provider.pipeline_model_parallel_size = 1
-provider.context_parallel_size = 1
-provider.sequence_parallel = True
-
-provider.finalize()
-model = provider.provide_distributed_model(wrap_with_ddp=False)
-
-# Other models:
-# bridge = AutoBridge.from_hf_pretrained("nvidia/Nemotron-H-4B-Base-8K", trust_remote_code=True)
-# bridge = AutoBridge.from_hf_pretrained("nvidia/Nemotron-H-47B-Base-8K", trust_remote_code=True)
-# bridge = AutoBridge.from_hf_pretrained("nvidia/Nemotron-H-56B-Base-8K", trust_remote_code=True)
-```
-
-### Export Megatron → HF
-```python
-# Convert from a Megatron checkpoint directory to HF format
-bridge.export_ckpt(
-    megatron_path="/results/nemotronh_8b/checkpoints/iter_0500000",
-    hf_path="./nemotronh-8b-hf-export",
-)
-```
-
-## Examples
-
-- Checkpoint conversion: [scripts/conversion/convert.sh](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/scripts/conversion/convert.sh)
-- Training scripts: [examples/models/train_any_basic.py](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/tutorials/recipes/llama/00_quickstart_pretrain.py)
-
-## Finetuning Recipes
-
-### Nemotron H 4B Finetuning
-
-#### LoRA Finetuning
-```python
-from megatron.bridge.recipes.nemotronh import nemotronh_4b_peft_config
-
-cfg = nemotronh_4b_peft_config(
-    tokenizer_path="nvidia/Nemotron-H-4B-Base-8K",
-    name="nemotronh_4b_lora",
-    pretrained_checkpoint="path/to/nemotronh/4b/checkpoint",
-    peft_scheme="lora",  # or "dora" for DoRA
-    train_iters=1000,
-    global_batch_size=128,
-    finetune_lr=1e-4,
-)
-```
-
-#### Full Supervised Finetuning (SFT)
-```python
-from megatron.bridge.recipes.nemotronh import nemotronh_4b_sft_config
-
-cfg = nemotronh_4b_sft_config(
-    tokenizer_path="nvidia/Nemotron-H-4B-Base-8K",
-    name="nemotronh_4b_sft",
-    pretrained_checkpoint="path/to/nemotronh/4b/checkpoint",
-    train_iters=1000,
-    global_batch_size=128,
-    finetune_lr=5e-6,  # Lower LR for full SFT
-)
-```
-
-### Nemotron H 8B Finetuning
-
-```python
-from megatron.bridge.recipes.nemotronh import nemotronh_8b_peft_config
-
-# LoRA finetuning
-cfg = nemotronh_8b_peft_config(
-    tokenizer_path="nvidia/Nemotron-H-8B-Base-8K",
-    name="nemotronh_8b_lora",
-    pretrained_checkpoint="path/to/nemotronh/8b/checkpoint",
-    peft_scheme="lora",
-    train_iters=1000,
-    global_batch_size=128,
-    finetune_lr=1e-4,
-)
-```
-
-### Nemotron H 47B Finetuning
-
-```python
-from megatron.bridge.recipes.nemotronh import nemotronh_47b_peft_config
-
-# LoRA finetuning (recommended for 47B)
-cfg = nemotronh_47b_peft_config(
-    tokenizer_path="nvidia/Nemotron-H-47B-Base-8K",
-    name="nemotronh_47b_lora",
-    pretrained_checkpoint="path/to/nemotronh/47b/checkpoint",
-    peft_scheme="lora",
-    train_iters=1000,
-    global_batch_size=128,
-    finetune_lr=1e-4,
-) 
-```
-
-### Nemotron H 56B Finetuning
-
-```python
-from megatron.bridge.recipes.nemotronh import nemotronh_56b_peft_config
-
-# LoRA finetuning (recommended for 56B)
-cfg = nemotronh_56b_peft_config(
-    tokenizer_path="nvidia/Nemotron-H-56B-Base-8K",
-    name="nemotronh_56b_lora",
-    pretrained_checkpoint="path/to/nemotronh/56b/checkpoint",
-    peft_scheme="lora",
-    train_iters=1000,
-    global_batch_size=128,
-    finetune_lr=1e-4,
-)
-```
-
-## Default Configurations
-
-### Nemotron H Models
-
-#### 4B - LoRA (1 node, 8 GPUs)
-- TP=1, PP=1, CP=1, LR=1e-4
-- Sequence Parallel: False
-- Precision: BF16 mixed
-- Optimized for single-GPU finetuning
-
-#### 4B - Full SFT (1 node, 8 GPUs)
-- TP=1, PP=1, CP=1, LR=5e-6
-- Sequence Parallel: False
-- Precision: BF16 mixed
-
-#### 8B - LoRA (1 node, 8 GPUs)
-- TP=1, PP=1, CP=1, LR=1e-4
-- Sequence Parallel: False
-- Precision: BF16 mixed
-
-#### 8B - Full SFT (1 node, 8 GPUs)
-- TP=2, PP=1, CP=1, LR=5e-6
-- Sequence Parallel: True
-- Precision: BF16 mixed
-
-#### 47B - LoRA (2+ nodes)
-- TP=4, PP=1, CP=1, LR=1e-4
-- Sequence Parallel: False
-- Precision: FP8 hybrid (recommended)
-
-#### 47B - Full SFT (4+ nodes)
-- TP=8, PP=1, CP=1, LR=5e-6
-- Sequence Parallel: True
-- Precision: FP8 hybrid
-
-#### 56B - LoRA (2+ nodes)
-- TP=4, PP=1, CP=1, LR=1e-4
-- Sequence Parallel: False
-- Precision: FP8 hybrid (recommended)
-
-#### 56B - Full SFT (4+ nodes)
-- TP=8, PP=1, CP=1, LR=5e-6
-- Sequence Parallel: True
-- Precision: FP8 hybrid
-
-## API Reference
-
-### Nemotron H
-- Nemotron H recipes: [bridge.recipes.nemotronh](../../apidocs/bridge/bridge.recipes.nemotronh.md)
-
-## Performance Optimizations
-
-### Memory Efficiency
-- **Selective Recomputation**: Reduces activation memory for larger models
-- **Sequence Parallelism**: Distributes sequence dimension across GPUs (enabled for 8B+)
-- **Manual GC**: Aggressive garbage collection for stable memory usage
-- **Precision-aware optimizer**: BF16/FP8 gradients with FP32 master weights
-
-### Compute Efficiency
-- **Mamba-2 Optimizations**: Efficient selective state space computations
-- **Hybrid Architecture**: Balanced mix of Mamba and Attention layers
-- **Squared ReLU**: Efficient activation function with good gradient properties
-- **RoPE Fusion**: Optional optimization for position embeddings
-- **Multi-Query Attention**: Reduced KV cache memory and compute
-
-### Hybrid Pattern Optimization
-The hybrid override pattern determines which layers use Mamba (M) vs Attention (*):
-- **Mamba layers**: Fast, memory-efficient, good for long-range dependencies
-- **Attention layers**: Better for complex reasoning and multi-token relationships
-- **Optimal patterns**: Pre-configured per model size based on extensive experimentation
-
-## Pipeline Parallelism Layouts
-
-Nemotron H models support several PP configurations with pre-defined layouts:
-- **PP=1**: No pipelining (default for most configurations)
-- **PP=2**: Supported with symmetric layer splits
-- **PP=4**: Supported for larger models (47B, 56B)
-- **VP (Virtual Pipeline)**: Supported for reducing pipeline bubbles
-
-## Hugging Face Model Cards
-
-### Nemotron H Models
-- **4B Base**: [nvidia/Nemotron-H-4B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-4B-Base-8K)
-- **8B Base**: [nvidia/Nemotron-H-8B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-8B-Base-8K)
-- **47B Base**: [nvidia/Nemotron-H-47B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-47B-Base-8K)
-- **56B Base**: [nvidia/Nemotron-H-56B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-56B-Base-8K)
-
-## Technical Resources
-
-### Research Papers
-- **Nemotron Technical Report**: [arXiv:2508.14444](https://arxiv.org/abs/2508.14444)
-- **Mamba-2**: [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://arxiv.org/abs/2405.21060)
-
-## Related Documentation
-
-- Recipe usage and customization: [Recipe usage](../../recipe-usage.md)
-- Training configuration: [Configuration overview](../../training/config-container-overview.md)
-- Training entry points: [Entry points](../../training/entry-points.md)
-- PEFT methods (LoRA, DoRA): [PEFT Guide](../../training/peft.md)
+See the [family overview](index.mdx) for supported Nemotron 3 and 3.5 models.
@@ -29,7 +29,7 @@ Megatron Bridge supports the following model families through bridge mappings an
 - **Llama**: Llama3, Llama3.1, Llama3.2, CodeLlama, Llama4
 - **Qwen**: Qwen2, Qwen2.5, Qwen3, Qwen3MoE, Qwen2.5VL
 - **DeepSeek**: DeepSeek V3, DeepSeek V4
-- **Nemotron**: Nemotron 3, Nemotron 3.5, Nemotron H (deprecated)
+- **Nemotron**: Nemotron 3, Nemotron 3.5
 - **NVIDIA Mamba**: Mamba variants and hybrid models
 
 For a complete list of bridge mappings, providers, and their parameters, see `bridge.models`.