Mistral AI models
Ministral all-rounders and the Devstral coding line.
Run on your device
Ministral 3
Mistral AI · Dec 2025Mistral's latest small model family. Fast inference, great for on-device use.
from 2.2 GBruns from 8 GB RAM256K contextApache 2.0
Devstral Small 2
Mistral AI · Dec 2025Mistral's agentic coding model. Tops open models on SWE-bench at its size — purpose-built for software engineering and code agents.
from 14.3 GBruns from 16 GB RAM384K contextApache 2.0
Community builds on Mistral models
Independent releases by other authors, built on this maker's open models - attributed to their own publishers, not to Mistral.