Model CoverageVision Language Models

Ministral3 VL

View as Markdown

Ministral3 is Mistral AI’s efficient small model series. The vision-capable variants support image-text inputs for multimodal tasks.

TaskImage-Text-to-Text
ArchitectureMistral3ForConditionalGeneration
Parameters3B – 14B
HF Orgmistralai

Available Models

  • Ministral-3-14B-Instruct-2512
  • Ministral-3-8B-Instruct-2512
  • Ministral-3-3B-Instruct-2512

Architecture

  • Mistral3ForConditionalGeneration

Example HF Models

ModelHF ID
Ministral-3 3B Instructmistralai/Ministral-3-3B-Instruct-2512
Ministral-3 8B Instructmistralai/Ministral-3-8B-Instruct-2512
Ministral-3 14B Instructmistralai/Ministral-3-14B-Instruct-2512

Example Recipes

RecipeDatasetDescription
ministral3_3b_medpix.yamlMedPix-VQASFT — Ministral3 3B on MedPix
ministral3_8b_medpix.yamlMedPix-VQASFT — Ministral3 8B on MedPix
ministral3_14b_medpix.yamlMedPix-VQASFT — Ministral3 14B on MedPix

Try with NeMo AutoModel

1. Clone and install from source (full instructions):

git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
uv sync --locked --all-groups --all-extras --extra vlm-media

2. Run the recipe from inside the repo:

uv run automodel --nproc-per-node=8 examples/vlm_finetune/mistral/ministral3_3b_medpix.yaml

1. Pull the container and mount a checkpoint directory:

docker run --gpus all -it --rm \
  --shm-size=8g \
  -v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
  nvcr.io/nvidia/nemo-automodel:26.06.00

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

cd /opt/Automodel

3. Install media dependencies (not installed in the container by default):

uv pip install ".[vlm-media]"

4. Run the recipe:

automodel --nproc-per-node=8 examples/vlm_finetune/mistral/ministral3_3b_medpix.yaml

See the Installation Guide and VLM Fine-Tuning Guide.

Fine-Tuning

See the VLM Fine-Tuning Guide.

Hugging Face Model Cards