Introducing Mistral Small 4
Simon Willison
Archived Mar 17, 2026
✓ Full text saved
Introducing Mistral Small 4 Big new release from Mistral today (despite the name) - a new Apache 2 licensed 119B parameter (Mixture-of-Experts, 6B active) model which they describe like this: Mistral Small 4 is the first Mistral model to unify the capabilities of our flagship models, Magistral for reasoning, Pixtral for multimodal, and Devstral for agentic coding, into a single, versatile model. It supports reasoning_effort="none" or reasoning_effort="high" , with the latter providing "equivalen
✦ Summarize
☆ Save
Full text archived locally
Simon Willison’s Weblog
Subscribe
Sponsored by: CodeRabbit — Planner helps 10x your coding agents while minimizing rework and AI slop. Try Now.
Introducing Mistral Small 4. Big new release from Mistral today (despite the name) - a new Apache 2 licensed 119B parameter (Mixture-of-Experts, 6B active) model which they describe like this:
Mistral Small 4 is the first Mistral model to unify the capabilities of our flagship models, Magistral for reasoning, Pixtral for multimodal, and Devstral for agentic coding, into a single, versatile model.
It supports reasoning_effort="none" or reasoning_effort="high", with the latter providing "equivalent verbosity to previous Magistral models".
The new model is 242GB on Hugging Face.
I tried it out via the Mistral API using llm-mistral:
llm install llm-mistral
llm mistral refresh
llm -m mistral/mistral-small-2603 "Generate an SVG of a pelican riding a bicycle"
I couldn't find a way to set the reasoning effort in their API documentation, so hopefully that's a feature which will land soon.
Also from Mistral today and fitting their -stral naming convention is Leanstral, an open weight model that is specifically tuned to help output the Lean 4 formally verifiable coding language. I haven't explored Lean at all so I have no way to credibly evaluate this, but it's interesting to see them target one specific language in this way.
Posted 16th March 2026 at 11:41 pm
Recent articles
My fireside chat about agentic engineering at the Pragmatic Summit - 14th March 2026
Perhaps not Boring Technology after all - 9th March 2026
Can coding agents relicense open source through a “clean room” implementation of code? - 5th March 2026
This is a link post by Simon Willison, posted on 16th March 2026.
ai 1913 generative-ai 1696 llms 1662 llm 564 mistral 66 pelican-riding-a-bicycle 100 llm-reasoning 95 llm-release 184
Monthly briefing
Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.
Pay me to send you less!
Sponsor & subscribe
Disclosures Colophon © 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026