Skip to content
local-ai

Devstral Small

Mistral AI · Code · 24B · 131k context · Released 25 July 2025

Commercial use permitted Open weights Runs on CPU Apple Silicon

Devstral Small is fine-tuned from Mistral Small 3.1 for agentic coding: exploring codebases, editing multiple files, and using tools, rather than one-shot code generation. Version 1.1 is the current release. It is a good fit for people running coding agents locally who want a permissive licence.

Strengths

  • Purpose-built for coding agents and multi-file, tool-driven work
  • Runs on a single 24GB card or a 32GB Mac
  • Apache 2.0, so usable commercially without conditions

Weaknesses

  • Specialised for agentic workflows, so less suited to plain chat
  • A 24B model still trails the largest coding models on the hardest tasks
  • Gets the most out of an agent harness like OpenHands, which adds setup

Hardware requirements

QuantisationApprox. VRAMNotes
Q4_K_M~14GBFits a 16GB card with short context
Q5_K_M~17GBA good balance on a 24GB card
Q8_0~25GBNear-lossless, needs 32GB or more
FP16~48GBFull precision, server or multi-GPU territory

Also runs on CPU (slower). Optimised builds available for Apple Silicon.

Licence

Apache 2.0 read the licence

Benchmarks

BenchmarkScoreSourceAs of
SWE-bench Verified53.6% Mistral AI model card (Devstral Small 1.1) July 2025

Availability

Recommended for

  • Running local coding agents on a single 24GB card
  • OpenHands and similar agent harnesses
  • Commercial coding work needing a permissive licence

Run it with

Related guides

Glossary

Our coverage

Catalogue entry last verified 30 July 2026. Specifications change; verify anything you are about to spend money on.