> 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-Medium-3.5-128B

> Use NeMo AutoModel to fine-tune Mistral-Medium-3.5-128B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.

[Mistral-Medium-3.5-128B](https://huggingface.co/mistralai/Mistral-Medium-3.5-128B) has a checked-in NeMo AutoModel recipe for image-text-to-text.
The Hugging Face configuration declares the `Mistral3ForConditionalGeneration` architecture.

## Fine-Tune Mistral-Medium-3.5-128B

Follow the [installation instructions](/get-started/installation), then review the checked-in recipe and
its declared topology below before choosing a local or cluster launcher.

Use the [Slurm launcher guide](/job-launchers/slurm-cluster) for the multi-node run.

## Choose a Workflow

| Goal                                         | Start Here                                                                                                                                        |
| -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| Run the primary recipe for this model        | Use the [recipe configuration](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/mistral3p5/mistral3p5_128b_medpix.yaml).  |
| Try another checked-in recipe for this model | Use the [alternate recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/mistral3p5/mistral3p5_128b_medpix_lora.yaml). |

### Configuration

| Setting  | Configuration                                             |
| -------- | --------------------------------------------------------- |
| Hardware | -                                                         |
| Strategy | FSDP2; tp\_size=8, pp\_size=8, cp\_size=1, ep\_size=1     |
| Nodes    | 8                                                         |
| Features | Activation checkpointing (activation\_checkpointing=true) |
| Advanced | torch.bfloat16                                            |

### More Recipes for This Model

* [`mistral3p5_128b_medpix_lora.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/mistral3p5/mistral3p5_128b_medpix_lora.yaml)

## Model Reference

### Model Architecture

| Property                        | Value                                    |
| ------------------------------- | ---------------------------------------- |
| Task                            | Image-text-to-text                       |
| Architecture                    | `Mistral3ForConditionalGeneration`       |
| NeMo AutoModel FP8 Architecture | `Mistral3FP8VLMForConditionalGeneration` |

### Available Models

* [`mistralai/Mistral-Medium-3.5-128B`](https://huggingface.co/mistralai/Mistral-Medium-3.5-128B)

## Related Resources

* [Vision-language model fine-tuning guide](/recipes-e2e-examples/gemma-3-3n)