Ministral 3
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