Skip to content

Text model · Mistral

Magistral Small: RAM and VRAM requirements

Magistral Small needs about 16 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~14 GB to download; KV cache and overhead add the rest), or about 27 GB at Q8_0. The lightest hardware that runs it is Apple M4 (24GB).

Mistral family · 24B params · released Jun 2025.

Shopping for hardware? See what runs Magistral Small →

License Apache-2.0 · Commercial OK ↓ 43.1K/mo ♥ 610 on HuggingFace
Q4_K_M GGUF
14 GB
Q8_0 GGUF
25 GB
Memory @ Q4 (4k)
~16 GB
Context
40 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?

Magistral 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 16 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)14 GB
+
KV cache (4k)1.2 GB
+
Overhead0.8 GB
=
Total16 GB

How context length changes it

4k context ~16 GB 32k context ~24.2 GB 128k context ~52.4 GB

Longer context grows the KV cache quickly: Magistral Small needs ~16 GB at 4k but ~52.4 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 Magistral Small generates at roughly ~27% 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) 14 GB
Q5_K_M 17.1 GB est
Q6_K 19.7 GB est
Q8_0 25 GB
FP16 47 GB

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

Run it

Ollama
$ ollama run magistral:24b

Which devices can run Magistral Small?

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 Magistral Small need?

At Q4_K_M, Magistral Small needs about 16 GB (weights ~14 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~27 GB.

What is the Q4_K_M GGUF file size of Magistral Small?

The Q4_K_M GGUF file is about 14 GB to download, and the Q8_0 GGUF is about 25 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~16 GB of memory at Q4_K_M.

Can Magistral Small run on a laptop?

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

Can I use Magistral Small commercially?

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

Understand the numbers

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

Mistral's open reasoning model, built on Small 3.1 with reinforcement learning. Tool use and vision.

Sources

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