Mistral AI logo

Ministral 3

Mistral AIOpen WeightsPending Human Review

Ministral 3 is Mistral’s third-generation family of small dense language and vision models, released alongside Mistral Large 3. Three sizes cover local, edge, and production deployments. Each size has base, instruct, and reasoning checkpoints with image understanding. The reasoning versions spend additional inference time on difficult tasks, while instruct models emphasize concise, inexpensive responses. All sizes are Apache-2.0 licensed; the 14B checkpoint documented here supports 256K context, with deployment memory varying by checkpoint and precision.

2025-12-02
3B, 8B, 14B
Dense Transformer with vision encoder
Apache-2.0

Specifications

Parameters
3B, 8B, 14B
Architecture
Dense Transformer with vision encoder
License
Apache-2.0
Context Window
262,144 tokens
Type
multimodal
Modalities
textimage

Benchmark Scores

Advanced Specifications

Model Family
Ministral
API Access
Available
Chat Interface
Not Available
Multilingual Support
Yes
Variants
3B Base/Instruct/Reasoning8B Base/Instruct/Reasoning14B Base/Instruct/Reasoning

Capabilities & Limitations

Capabilities
visionreasoningmultilinguallocal inference
Known Limitations
Smaller models trade broad capability for lower inference costReasoning variants increase output length and latency
Notable Use Cases
edge assistantslocal document analysissmall reasoning agents

Related Models