Skip to content
localmodel.run

Text model · Mistral

Devstral Small: RAM and VRAM requirements

Devstral Small 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 Jul 2025.

Shopping for hardware? See what runs Devstral Small →

License Apache-2.0 · Commercial OK ↓ 116.3K/mo ♥ 368 on HuggingFace
Q4_K_M GGUF
13.35 GB
Q8_0 GGUF
23.33 GB
Memory @ Q4 (4k)
~15.4 GB
Context
128 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 runs on 15 of 40 tracked devices at Q4_K_M.

13 run well 2 tight fit 25 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 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 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 47.2 GB

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

Run it

Ollama
$ ollama run devstral:24b
llama.cpp
$ llama-cli -hf mistralai/Devstral-Small-2507_gguf:Q4_K_M
LM Studio
$ lms get mistralai/Devstral-Small-2507_gguf

Which devices can run Devstral Small?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

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

Next size down ERNIE 4.5 21B-A3B 21B Next size up Gemma 4 26B-A4B 26.5B

Similar models

Head-to-head

FAQ

How much VRAM or RAM does Devstral Small need?

At Q4_K_M, Devstral Small 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?

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 run on a laptop?

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

Can I use Devstral Small commercially?

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

Understand the numbers

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

Mistral's coding-agent model, strong on SWE-bench. A community favorite for local Cline and OpenHands.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.