> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/latest/model-coverage/vision-language-models/mistralai/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 AI

> Browse NeMo AutoModel coverage for Mistral AI vision language models.

* [`Devstral-2-123B-Instruct-2512`](/model-coverage/vision-language-models/mistralai/Devstral-2-123B-Instruct-2512)
* [`Ministral-3-14B-Reasoning-2512`](/model-coverage/vision-language-models/mistralai/Ministral-3-14B-Reasoning-2512)
* [`Ministral-3-3B-Instruct-2512`](/model-coverage/vision-language-models/mistralai/Ministral-3-3B-Instruct-2512)
* [`Ministral-3-8B-Reasoning-2512`](/model-coverage/vision-language-models/mistralai/Ministral-3-8B-Reasoning-2512)
* [`Mistral-Medium-3.5-128B`](/model-coverage/vision-language-models/mistralai/Mistral-Medium-3.5-128B)
* [`Mistral-Small-4-119B-2603`](/model-coverage/vision-language-models/mistralai/Mistral-Small-4-119B-2603)

> Browse NeMo AutoModel coverage for Mistral AI vision language models.

## Docs

- [Devstral-2-123B-Instruct-2512](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/vision-language-models/mistralai/Devstral-2-123B-Instruct-2512.md): Fine-tune Devstral-2-123B-Instruct-2512 for text generation with NeMo AutoModel using the checked-in single-node tensor-parallel LoRA recipe.
- [Ministral-3-14B-Reasoning-2512](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/vision-language-models/mistralai/Ministral-3-14B-Reasoning-2512.md): Use NeMo AutoModel to fine-tune Ministral-3-14B-Reasoning-2512 for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Ministral-3-3B-Instruct-2512](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/vision-language-models/mistralai/Ministral-3-3B-Instruct-2512.md): Reference Ministral-3-3B-Instruct-2512 checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [Ministral-3-8B-Reasoning-2512](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/vision-language-models/mistralai/Ministral-3-8B-Reasoning-2512.md): Use NeMo AutoModel to fine-tune Ministral-3-8B-Reasoning-2512 for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Mistral-Medium-3.5-128B](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/vision-language-models/mistralai/Mistral-Medium-3.5-128B.md): 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-Small-4-119B-2603](https://docs.nvidia.com/nemo/automodel/latest/model-coverage/vision-language-models/mistralai/Mistral-Small-4-119B-2603.md): Use Mistral-Small-4-119B-2603 with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup, and model reference details.