Pixtral 12B
The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent: https://x.com/mistralai/status/1833758285167722836.
Input
Output
Context
33K
Max Output
4K
Parameters
12B
Technical Specifications
Model TypeVision
Context Window33K
Max Output Tokens4K
Parameters12B
Training Cutoff—
Licenseapache-2.0
Capabilities
Input Modalities
textimage
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generationvision
Estimated GPU Requirements for Pixtral 12B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Apr 10, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.