Pixtral 12B
Open Weights
Mistral AI
Mistral's first multimodal model (September 2024), a 12B open-weight model with a dedicated vision encoder that understands images alongside text at native resolution. Released under Apache 2.0, it brought strong open multimodal performance to consumer-scale hardware.
Strengths
- Open-weight 12B multimodal under Apache 2.0
- Understands images at native resolution
- 128K context window
- Strong open multimodal performance
- Runs on a single GPU
Caveats
- 12B ceiling below larger multimodal models
- No audio input
- Superseded by Pixtral Large for peak quality
- Vendor
- Mistral AI
- Context Window
- 128,000 tokens
- License
- Apache-2.0
- Release Date
- 2024-09-17
- Modalities
- textimage
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
Open weights under Apache 2.0 - free to self-host; also served via the Mistral API. 12B runs on a single GPU.