Dataset updated 2026-11-12Devstral Small 2 24B
Devstral Small 2 24B loads in 15.2 GB at Q4_K_M, comfortably from 32 GB of memory, Macs included, starting at the MacBook Air M5 24GB. Below is the memory math we ran for it, the smallest card that fits, and the fastest machine we track.
- Parameters
- 24B
- Format
- Q4_K_M
- Min memory
- 24 GB
- Best for
- Agentic coding, Software engineering
How much memory does Devstral Small 2 24B need?
Devstral Small 2 24B is a 24B dense model built for agentic coding, software engineering. The weights alone take 15.2 GB at Q4_K_M; add context and the OS, and it belongs in the 32 GB memory class. Every number below comes from the ModelFit engine: speeds are estimates, labeled est., because we do not benchmark hardware ourselves.
KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).
Which machines run Devstral Small 2 24B?
- Smallest GPU
- AMD Radeon RX 7900 XTest. 39 tok/s · 20 GB VRAMtypical error 50%
- Fastest
- NVIDIA GeForce RTX 5090est. 93 tok/stypical error 5%
- Runs on a Mac?
- MacBook Air M5 24GBest. 9 tok/stypical error 10%
Verdicts come from the same engine that powers our fit checker: memory capacity first, bandwidth for speed. How we compute these numbers · What typical error means · Hugging Face model card
More Mistral models
12 pagesGet told when a better model fits your MacBook Air M5 16 GB
Get one email when a new open-weight model is a better fit for this machine.
For: MacBook Air M5 16 GB
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Config reports
No speed test run for this model yet. Run the speed test: npx @modelfit/cli@latest bench
Share your config
Frequently asked questions
How much memory does Devstral Small 2 24B need?
15.2 GB for the Q4_K_M weights, plus ~4.0 GB of KV-cache at 16k context, about 19.2 GB total. Comfortable from 32 GB of VRAM or unified memory.
Does Devstral Small 2 24B run on a Mac?
Yes, from the MacBook Air M5 24GB (est. 9 tok/s, typical error 10%). Unified memory means the RAM budget is the only limit.
What is the smallest GPU for Devstral Small 2 24B?
The AMD Radeon RX 7900 XT (20 GB VRAM) is the smallest tracked card that runs Devstral Small 2 24B comfortably, est. 39 tok/s, typical error 50%.
Cite this page
ModelFit: Devstral Small 2 24B, specs, memory math and hardware verdicts. https://modelfit.io/models/devstral-small-2-24b/ (dataset updated 2026-11-12, CC BY 4.0).