Pixtral 12B
by Mistral AI · open-source · Last verified 2026-03-17
Mistral AI's natively multimodal model with a dedicated 400M parameter vision encoder alongside a 12B language backbone. Processes images at their native resolution without fixed-size tokenization.
https://mistral.ai/news/pixtral-12b/ ↗C+
C+—Average
Adoption: BQuality: B+Freshness: B+Citations: C+Engagement: F
Specifications
- License
- Apache 2.0
- Pricing
- open-source
- Capabilities
- text-generation, image-understanding, visual-qa, chart-analysis, document-understanding
- Integrations
- huggingface, vllm, ollama
- Use Cases
- visual-qa, document-analysis, chart-interpretation, image-captioning, multimodal-chatbots
- API Available
- Yes
- Parameters
- 12B
- Context Window
- 128K tokens
- Modalities
- text, image
- Training Cutoff
- Mid 2024
- Tags
- llm, open-source, multimodal, vision, natively-multimodal, mistral
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
53.75Adoption
62
Quality
76
Freshness
72
Citations
55
Engagement
0