> This page is for version 0.5.0 · 26.06.
> For other versions, use one of these documentation indexes:
> - Nightly (default): https://docs.nvidia.com/nemo/automodel/nightly/llms.txt
> - Latest: https://docs.nvidia.com/nemo/automodel/latest/llms.txt
> - 0.5.0 · 26.06: https://docs.nvidia.com/nemo/automodel/v0.5/llms.txt
> - 0.4.0 · 26.04: https://docs.nvidia.com/nemo/automodel/v0.4/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# Nemotron-3-Nano-Omni

[Nemotron-3-Nano-Omni-30B-A3B-Reasoning](https://huggingface.co/nvidia) is NVIDIA's
omnimodal reasoning model. It pairs a NemotronH (hybrid Mamba-2 + Attention) MoE
language backbone with a RADIO v2.5-H vision encoder and a Parakeet (FastConformer)
sound encoder, supporting interleaved text, image, and audio inputs.

> **Info**
>
> |                  |                                         |
> | ---------------- | --------------------------------------- |
> | **Task**         | Omnimodal (Text·Image·Audio)            |
> | **Architecture** | `NemotronH_Nano_Omni_Reasoning_V3`      |
> | **Parameters**   | 30B total / 3B active                   |
> | **HF Org**       | [nvidia](https://huggingface.co/nvidia) |

## Available Models

* **Nemotron-3-Nano-Omni-30B-A3B-Reasoning**: 30B total, 3B activated (MoE)

## Architecture

* `NemotronH_Nano_Omni_Reasoning_V3`

## Example Recipes

| Recipe                                                                                                                                                        | Dataset | Description                 |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- | --------------------------- |
| [nemotron\_omni\_cord\_v2.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/nemotron_omni/nemotron_omni_cord_v2.yaml)            | CORD-v2 | Full SFT — receipt parsing  |
| [nemotron\_omni\_cord\_v2\_peft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/nemotron_omni/nemotron_omni_cord_v2_peft.yaml) | CORD-v2 | LoRA PEFT — receipt parsing |

## Try with NeMo AutoModel

**1. Install** ([NeMo AutoModel](/get-started/installation)):

```bash
pip install "nemo-automodel[vlm,vlm-media]"
```

**2. Clone the repo** to get the example recipes:

```bash
git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
```

**3. Run the recipe** from inside the repo (8x H100 example):

```bash
automodel examples/vlm_finetune/nemotron_omni/nemotron_omni_cord_v2.yaml --nproc-per-node 8
```

For a full walkthrough — dataset preparation, SFT vs. LoRA configs, and
post-training inference — see the
[Nemotron-Omni guide](/recipes-e2e-examples/nemotron-omni).