> 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.

# Mistral-Small-4

[Mistral-Small-4-119B](https://huggingface.co/mistralai/Mistral-Small-4-119B-Instruct-2512) is Mistral AI's multimodal MoE model supporting both text and image inputs at scale.

|                  |                                               |
| ---------------- | --------------------------------------------- |
| **Task**         | Image-Text-to-Text                            |
| **Architecture** | `MistralForConditionalGeneration`             |
| **Parameters**   | 119B (MoE)                                    |
| **HF Org**       | [mistralai](https://huggingface.co/mistralai) |

## Available Models

* **Mistral-Small-4-119B-Instruct-2512**

## Architecture

* `MistralForConditionalGeneration`

## Example HF Models

| Model                         | HF ID                                                                                                                 |
| ----------------------------- | --------------------------------------------------------------------------------------------------------------------- |
| Mistral-Small-4 119B Instruct | [`mistralai/Mistral-Small-4-119B-Instruct-2512`](https://huggingface.co/mistralai/Mistral-Small-4-119B-Instruct-2512) |

## Example Recipes

| Recipe                                                                                                                          | Dataset    | Description                     |
| ------------------------------------------------------------------------------------------------------------------------------- | ---------- | ------------------------------- |
| [mistral4\_medpix.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/mistral4/mistral4_medpix.yaml) | MedPix-VQA | SFT — Mistral-Small-4 on MedPix |

## Try with NeMo AutoModel

**1. Install** ([full instructions](/get-started/installation)):

```bash
pip install nemo-automodel
```

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

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

This recipe was validated on **4 nodes × 8 GPUs (32 H100s)**. See the [Launcher Guide](/job-launchers/slurm-cluster) for multi-node setup.

**3. Run the recipe** from inside the repo:

```bash
automodel --nproc-per-node=8 examples/vlm_finetune/mistral4/mistral4_medpix.yaml
```

**1. Pull the container** and mount a checkpoint directory:

```bash
docker run --gpus all -it --rm \
  --shm-size=8g \
  -v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
  nvcr.io/nvidia/nemo-automodel:26.04.00
```

**2.** Navigate to the AutoModel directory (where the recipes are):

```bash
cd /opt/Automodel
```

**3. Run the recipe**:

```bash
automodel --nproc-per-node=8 examples/vlm_finetune/mistral4/mistral4_medpix.yaml
```

See the [Installation Guide](/get-started/installation) and [VLM Fine-Tuning Guide](/recipes-e2e-examples/gemma-3-3n).

## Fine-Tuning

See the [VLM Fine-Tuning Guide](/recipes-e2e-examples/gemma-3-3n).

## Hugging Face Model Cards

* [mistralai/Mistral-Small-4-119B-Instruct-2512](https://huggingface.co/mistralai/Mistral-Small-4-119B-Instruct-2512)