Model CoverageVision Language ModelsMistral AIMinistral-3-3B-Instruct-2512

Ministral-3-3B-Instruct-2512

View as Markdown

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

Set up NeMo AutoModel with the latest container or follow the installation instructions.

Fine-Tune Ministral-3-3B-Instruct-2512

From the repository root, run:

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

Choose a Workflow

GoalStart Here
Supervised fine-tuning (SFT) - Ministral3 3B on MedPixUse ministral3_3b_medpix.yaml. Dataset: MedPix-VQA.

Model Reference

Model Architecture

PropertyValue
TaskImage-Text-to-Text
ArchitectureMistral3ForConditionalGeneration
Parameters3B
Hugging Face Organizationmistralai

Available Models

ModelHF ID
Ministral-3 3B Instructmistralai/Ministral-3-3B-Instruct-2512
Ministral-3-3B-Reasoning-2512mistralai/Ministral-3-3B-Reasoning-2512