Devstral Small 2 (24B)

Mistral AI

Free

Get

MLX Score1.3

PriceFreeno paid plan

RunsOn your Mac

DeveloperMistral AI

LicenceOpenApache-2.0

CategoryModels

Mac14.0+macOS or later

Devstral Small 2 is a 24-billion-parameter model from Mistral AI made for software-engineering agents: using tools to explore a codebase and edit several files.

Mistral says it's light enough for a Mac with 32 GB of memory. A 4-bit MLX build is about 15 GB, and on mlx.app's estimate it already fits a 24 GB Mac.

Open weights under Apache 2.0. Run locally, nothing leaves your Mac.

How to Get It

Run it on your MacSee how

WebsiteVisit

Official downloads only. MLX never re-hosts an app, and never runs a command for you.

MLX Score

1.3out of 5

Hugging Face downloads and likesahead of 7%

Hugging Face: 138,229 downloads (30 days), 712 likes · read 2026-11-02

Ranked against the open models listings, from real public data only. How the score works.

Information

Developer: Mistral AI
Category: Open models
Price: Free (Open weights, free to download.)
Your data: Runs on your Mac
Licence: Apache-2.0
Mac: macOS 14.0 or later
iPhone and iPad: —
Needs: 24 GB memory
Links: Website · Hugging Face
Facts checked: 2026-11-01

Sources

huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512 · Apache-2.0, 24B, agentic coding, 'a Mac with 32GB RAM' · checked 2026-11-01huggingface.co/mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit · 4-bit MLX build (about 15 GB) · checked 2026-11-01ml-explore.github.io/mlx/build/html/install.html · macOS 14.0 minimum (MLX needs Apple silicon and macOS 14.0+) · checked 2026-11-01mlx.app/run/devstral-small-2 · memory: smallest Mac (24 GB) where the 4-bit MLX build fits with room for context, from lib/compare (75% of unified memory usable) · checked 2026-11-01Icon from Hugging Face

See All