Skip to content

Text model · Mistral

Devstral Small 2 24B: RAM and VRAM requirements

Devstral Small 2 24B needs about 15.4 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~13.35 GB to download; KV cache and overhead add the rest), or about 25.3 GB at Q8_0. The lightest hardware that runs it is Apple M4 (24GB).

Mistral family · 24B params · released Dec 2025 · 969.9K Ollama pulls.

Shopping for hardware? See what runs Devstral Small 2 24B →

License Apache-2.0 · Commercial OK ↓ 223.9K/mo ♥ 656 on HuggingFace
Q4_K_M GGUF
13.35 GB
Q8_0 GGUF
23.33 GB
Memory @ Q4 (4k)
~15.4 GB
Context
384 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

Devstral Small 2 24B runs on 15 of 43 tracked devices at Q4_K_M.

13 run well 2 tight fit 28 too small
Fit check Q4_K_M
No, not enough memory
needs 15.4 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)13.35 GB
+
KV cache (4k)1.2 GB
+
Overhead0.8 GB
=
Total15.4 GB

How context length changes it

4k context ~15.4 GB 32k context ~23.6 GB 128k context ~51.8 GB

Longer context grows the KV cache quickly: Devstral Small 2 24B needs ~15.4 GB at 4k but ~51.8 GB at 128k, which can push it past a device that fits it at a short context.

Speed drops too: every token re-reads the KV cache, so at 128k context Devstral Small 2 24B generates at roughly ~26% of its short-context speed. How this is estimated.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 10.1 GB est
Q3_K_M 11.7 GB est
Q4_K_M (default) 13.35 GB
Q5_K_M 17.1 GB est
Q6_K 19.7 GB est
Q8_0 23.33 GB
FP16 48.03 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run devstral-small-2:24b
llama.cpp
$ llama-cli -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_M
LM Studio
$ lms get unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF

Which devices can run Devstral Small 2 24B?

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Similar models

Head-to-head

FAQ

How much VRAM or RAM does Devstral Small 2 24B need?

At Q4_K_M, Devstral Small 2 24B needs about 15.4 GB (weights ~13.35 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~25.3 GB.

What is the Q4_K_M GGUF file size of Devstral Small 2 24B?

The Q4_K_M GGUF file is about 13.35 GB to download, and the Q8_0 GGUF is about 23.33 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~15.4 GB of memory at Q4_K_M.

Can Devstral Small 2 24B run on a laptop?

Devstral Small 2 24B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Can I use Devstral Small 2 24B commercially?

Yes. Devstral Small 2 24B is licensed Apache-2.0, which permits commercial use.

Understand the numbers

Short guides to the ideas behind Devstral Small 2 24B's memory and quant figures.

Mistral's agentic coding 24B, second generation (supersedes the 2505/2507 Devstral Small already tracked): 384K context (config 393216), Apache-2.0. Sizes from unsloth's GGUF repo, matching the Ollama tag listing.

Sources

Last validated 2026-09-07. Memory figures are estimates. See methodology.