@@ -11,33 +11,33 @@
 </div>
 
 ## 📣 News
-- [05/06/2026] [**Gemma 4 VL 26B-A4B**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/vlm/gemma4_vl) is now supported! Checkpoint conversion, SFT, and PEFT (LoRA) recipes for Google's MoE vision-language model (26B total / 4B active params, 128 experts top-k=8, dual sliding/global attention with K=V tying on full-attention layers) are available on **main**. See the [examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/gemma4_vl/README.md) for the full walkthrough.
+- [05/06/2026] [**Gemma 4 VL 26B-A4B**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/gemma/gemma4_vl) is now supported! Checkpoint conversion, SFT, and PEFT (LoRA) recipes for Google's MoE vision-language model (26B total / 4B active params, 128 experts top-k=8, dual sliding/global attention with K=V tying on full-attention layers) are available on **main**. See the [examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/gemma/gemma4_vl/README.md) for the full walkthrough.
 
 - [04/28/2026] Day 0 support for [**Nemotron-3 Nano Omni**](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16), a 30B-A3B MoE multimodal model that jointly processes image, video, audio, and text. Checkpoint conversion, SFT, and LoRA recipes are available on the [`nemotron_3_omni`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/nemotron_3_omni) branch — see the [examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/nemotron_3_omni/examples/models/vlm/nemotron_3_omni/README.md) for the full walkthrough.
 
 - [04/19/2026] [**Qwen3.6-35B-A3B**](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) is now supported! Qwen3.6 uses the same architecture as Qwen3.5 VL MoE (`Qwen3_5MoeForConditionalGeneration`) and works with the existing [Qwen3.5-VL bridge](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/src/megatron/bridge/models/qwen_vl) out of the box — no code changes needed. HF→Megatron conversion and inference verified.
 
 - [04/16/2026] **Megatron Bridge 0.4.0 released!** New model support (Kimi 2.5, Nemotron 3 Super, Qwen 3.5 VL, MiniMax M2, Sarvam, MiMo, and more), diffusion model collection, sequence-packing improvements, FP8 export, pruning & quantization, Transformers 5.x compatibility, and Python 3.12 migration. Huge thanks to our community contributors: [@HollowMan6](https://github.com/HollowMan6), [@shaltielshmid](https://github.com/shaltielshmid), [@jaeminh](https://github.com/jaeminh), [@pavelgein](https://github.com/pavelgein), [@ShiftyBlock](https://github.com/ShiftyBlock), [@erictang000](https://github.com/erictang000), [@eternally-z](https://github.com/eternally-z), [@Hayak3](https://github.com/Hayak3), and [@mohit-sarvam](https://github.com/mohit-sarvam)! See the [full release notes](https://github.com/NVIDIA-NeMo/Megatron-Bridge/releases/tag/v0.4.0).
 
-- [04/12/2026] [**MiniMax-M2.5 / M2.7**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/minimax_m2) are now supported! Both models share the same architecture as MiniMax-M2 and work with the existing bridge out of the box — checkpoint conversion and inference verified on real FP8 checkpoints.
+- [04/12/2026] [**MiniMax-M2.5 / M2.7**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/minimax/minimax_m2) are now supported! Both models share the same architecture as MiniMax-M2 and work with the existing bridge out of the box — checkpoint conversion and inference verified on real FP8 checkpoints.
 
-- [04/10/2026] [**Qwen3-ASR**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/audio_lm/qwen3_asr) is now supported! Checkpoint conversion and inference for [Qwen3's ASR model](https://github.com/QwenLM/Qwen3-ASR) are available on **main**.
+- [04/10/2026] [**Qwen3-ASR**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/qwen/qwen3_asr) is now supported! Checkpoint conversion and inference for [Qwen3's ASR model](https://github.com/QwenLM/Qwen3-ASR) are available on **main**.
 
 - [04/09/2026] [**Bailing MoE V2**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/bailing) is now supported! Checkpoint conversion and inference for the Bailing MoE V2 model are available on **main**. Thank you to [@ccclyu](https://github.com/ccclyu) for the community contribution!
 
 - [04/07/2026] Megatron Bridge’s PEFT support was featured at [PyTorch Conference Europe 2026 Talk](https://pytorchconferenceeu2026.sched.com/event/2Juce/optimizing-reinforcement-learning-at-trillion-parameter-scale-songlin-jiang-aalto-university-mind-lab).
 
-- [04/01/2026] [**Kimi K2.5 VL**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/vlm/kimi_k25_vl) is now supported! Checkpoint conversion, inference, and training recipes for [Moonshot AI’s Kimi-K2.5-VL](https://huggingface.co/moonshotai/Kimi-K2.5) vision-language model are available on **main**.
+- [04/01/2026] [**Kimi K2.5 VL**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/kimi/kimi_k25_vl) is now supported! Checkpoint conversion, inference, and training recipes for [Moonshot AI’s Kimi-K2.5-VL](https://huggingface.co/moonshotai/Kimi-K2.5) vision-language model are available on **main**.
 
 - [03/31/2026] **Agent Skills for Megatron Bridge!** We've added a [`skills/`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/skills) directory with structured guides that AI coding agents (Cursor, Claude Code, Codex, etc.) can use to help you add model support, set up dev environments, tune performance, and more. Try them out, and PRs to improve or add new skills are very welcome!
 
-- [03/26/2026] [**Nemotron 3 Super**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron_3) is now on **main**! Checkpoint conversion and SFT/LoRA recipes (120B-A12B) are available in the main branch. Read the [blog post](https://developer.nvidia.com/blog/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning/).
+- [03/26/2026] [**Nemotron 3 Super**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron/nemotron_3) is now on **main**! Checkpoint conversion and SFT/LoRA recipes (120B-A12B) are available in the main branch. Read the [blog post](https://developer.nvidia.com/blog/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning/).
 
 - [03/12/2026] **Deprecating Python 3.10 support:** We're officially dropping Python 3.10 support with the upcoming 0.4.0 release. Downstream applications must raise their lower boundary to 3.12 to stay compatible with Megatron-Bridge.
 
 - [12/16/2025] [Mind Lab](https://macaron.im/mindlab) successfully used Megatron-bridge and [VeRL](https://github.com/volcengine/verl) to trained GRPO Lora for Trillion-parameter model on 64 H800 - See their [techblog](https://macaron.im/mindlab/research/building-trillion-parameter-reasoning-rl-with-10-gpus).
 
-- [12/15/2025] Day 0 support for [NVIDIA-NeMotron-3-Nano-30B-A3B-FP8](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8)! [Reproducible code](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron_3/nano) and custom NGC container: [nvcr.io/nvidia/nemo:25.11.nemotron_3_nano](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo?version=25.11.nemotron_3_nano)
+- [12/15/2025] Day 0 support for [NVIDIA-NeMotron-3-Nano-30B-A3B-FP8](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8)! [Reproducible code](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron/nemotron_3/nano) and custom NGC container: [nvcr.io/nvidia/nemo:25.11.nemotron_3_nano](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo?version=25.11.nemotron_3_nano)
 
 ## Overview
 
 
@@ -19,7 +19,7 @@ Megatron Bridge supports the following LLM families:
 | **LLaMA Nemotron** | [llama-nemotron.md](llama-nemotron.md) | NVIDIA LLaMA Nemotron models |
 | **Mistral** | [mistral.md](mistral.md) | Mistral AI models |
 | **Moonlight** | [moonlight.md](moonlight.md) | Moonlight model family |
-| **Nemotron-3** | [nemotron3.md](nemotron3.md) | NVIDIA Nemotron-3 models |
+| **Nemotron-3 Nano** | [nemotron3-nano.md](nemotron3-nano.md) | NVIDIA Nemotron-3 Nano models |
 | **Nemotron-3 Super** | [nemotron3-super.md](nemotron3-super.md) | NVIDIA Nemotron-3 Super models |
 | **Nemotron-H** | [nemotronh.md](nemotronh.md) | NVIDIA Nemotron-H models |
 | **OLMoE** | [olmoe.md](olmoe.md) | OLMoE (Open Language Model - Mixture of Experts) |
 
@@ -182,7 +182,7 @@ uv run python -m torch.distributed.run --nproc-per-node=8 run/run_recipe.py \
 - Gemma 3 1B: https://huggingface.co/google/gemma-3-1b-it
 
 ## Related Docs
-- Gemma3 Vision-Language Models: [Gemma 3 VL](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/gemma3_vl/README.md)
+- Gemma3 Vision-Language Models: [Gemma 3 VL](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/gemma/gemma3_vl/README.md)
 - Recipe usage: [Recipe usage](../../recipe-usage.md)
 - Customizing the training recipe configuration: [Configuration overview](../../training/config-container-overview.md)
 - Training entry points: [Entry points](../../training/entry-points.md)
@@ -15,9 +15,9 @@ llama3.md
 llama-nemotron.md
 mistral.md
 moonlight.md
-nemotron3.md
+nemotron3-nano.md
 nemotron3-super.md
 nemotronh.md
 olmoe.md
 qwen.md
-```
+```
@@ -38,7 +38,7 @@ uv run python examples/conversion/convert_checkpoints.py export  \
 BLEND_PATH=/path/to/dataset/blend
 TOKENIZER_MODEL=/path/to/tiktok/tokenizer/model
 
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/pretrain_nemotron_3_nano.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/nano/pretrain_nemotron_3_nano.py \
 --per-split-data-args-path=${BLEND_PATH} \
 --tokenizer-model=${TOKENIZER_MODEL} \
 train.global_batch_size=3072 \
@@ -56,7 +56,7 @@ Notes:
 
 ### Full Parameter Fine-Tuning
 ```bash
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/finetune_nemotron_3_nano.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/nano/finetune_nemotron_3_nano.py \
 train.global_batch_size=128 \
 train.train_iters=100 \
 scheduler.lr_warmup_iters=10 \
@@ -72,7 +72,7 @@ Notes:
 ### LoRA Fine-Tuning
 To enable LoRA fine-tuning, pass `--peft lora` to script
 ```bash
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/finetune_nemotron_3_nano.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/nano/finetune_nemotron_3_nano.py \
 --peft lora \
 train.global_batch_size=128 \
 train.train_iters=100 \
 
@@ -120,7 +120,7 @@ uv run python -m torch.distributed.run --nproc-per-node=8 examples/conversion/co
 BLEND_PATH=/path/to/dataset/blend.json
 CHECKPOINT_DIR=/path/to/checkpoints
 
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/pretrain_nemotron_3_super.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/super/pretrain_nemotron_3_super.py \
 --per-split-data-args-path=${BLEND_PATH} \
 logger.wandb_project=your_project \
 logger.wandb_entity=nvidia \
@@ -153,7 +153,7 @@ For quick testing without a dataset:
 ```bash
 CHECKPOINT_DIR=/path/to/checkpoints
 
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/pretrain_nemotron_3_super.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/super/pretrain_nemotron_3_super.py \
 logger.wandb_project=your_project \
 logger.wandb_entity=nvidia \
 checkpoint.load=${CHECKPOINT_DIR} \
@@ -179,7 +179,7 @@ Notes:
 MEGATRON_PATH=/path/to/pretrained/megatron/ckpt
 CHECKPOINT_DIR=/path/to/finetuned/checkpoints
 
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/finetune_nemotron_3_super.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/super/finetune_nemotron_3_super.py \
 logger.wandb_project=your_project \
 logger.wandb_entity=nvidia \
 logger.log_interval=5 \
@@ -208,7 +208,7 @@ To enable LoRA fine-tuning, pass `--peft lora` to the script:
 MEGATRON_PATH=/path/to/pretrained/megatron/ckpt
 CHECKPOINT_DIR=/path/to/lora/checkpoints
 
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/finetune_nemotron_3_super.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/super/finetune_nemotron_3_super.py \
 --peft lora \
 logger.wandb_project=your_project \
 logger.wandb_entity=nvidia \
@@ -303,7 +303,7 @@ After quantization, further improve model quality with QAT by continuing trainin
 MEGATRON_PATH=/path/to/quantized/megatron/ckpt
 CHECKPOINT_DIR=/path/to/qat/checkpoints
 
-uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron_3/qat_nemotron_3_super.py \
+uv run python -m torch.distributed.run --nproc-per-node=8 examples/models/nemotron/nemotron_3/super/qat_nemotron_3_super.py \
 --megatron-load-path=${MEGATRON_PATH} \
 --seq-length=8192 \
 --packed-sequence \
 
@@ -46,7 +46,7 @@ Gemma 3 VL builds on the Gemma 3 architecture with additional multimodal capabil
 
 ## Examples
 
-For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [Gemma 3 VL Examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/gemma3_vl/README.md).
+For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [Gemma 3 VL Examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/gemma/gemma3_vl/README.md).
 
 ## Hugging Face Model Cards
 
 
@@ -12,4 +12,4 @@ PEFT on image-text datasets. The finetuned model can be re-exported to
 
 For the full setup, conversion, inference, training, and LoRA merge /
 adapter export workflows, see
-[`examples/models/vlm/gemma4_vl/README.md`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/gemma4_vl/README.md).
+[`examples/models/gemma/gemma4_vl/README.md`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/gemma/gemma4_vl/README.md).
@@ -41,7 +41,7 @@ GLM-4.5V combines efficient sparse MoE language modeling with multimodal capabil
 
 ## Examples
 
-For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [GLM-4.5V Examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/glm_45v/README.md).
+For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [GLM-4.5V Examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/glm/glm_45v/README.md).
 
 ## Hugging Face Model Cards
 
 
@@ -51,7 +51,7 @@ Ministral 3 combines efficient language modeling with multimodal capabilities:
 
 ## Examples
 
-For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [Ministral 3 Examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/ministral3/README.md).
+For checkpoint conversion, inference, finetuning recipes, and step-by-step training guides, see the [Ministral 3 Examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/ministral/ministral3/README.md).
 
 ## Hugging Face Model Cards