Skip to content

Text model · Mistral

Mistral Small 3 24B: RAM and VRAM requirements

Mistral Small 3 24B needs about 16.3 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~14.33 GB to download; KV cache and overhead add the rest), or about 27.1 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 4090 (24GB).

Mistral family · 24B params · released Jun 2025 · 1.3M Ollama pulls · LMArena Elo 1357.

Shopping for hardware? See what runs Mistral Small 3 24B →

License Apache-2.0 · Commercial OK ↓ 312.7K/mo ♥ 600 on HuggingFace
Q4_K_M GGUF
14.33 GB
Q8_0 GGUF
25.05 GB
Memory @ Q4 (4k)
~16.3 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?

Mistral Small 3 24B runs on 13 of 40 tracked devices at Q4_K_M.

13 run well 0 tight fit 27 too small
Fit check Q4_K_M
No, not enough memory
needs 16.3 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)14.33 GB
+
KV cache (4k)1.2 GB
+
Overhead0.8 GB
=
Total16.3 GB

How context length changes it

4k context ~16.3 GB 32k context ~24.5 GB 128k context ~52.7 GB

Longer context grows the KV cache quickly: Mistral Small 3 24B needs ~16.3 GB at 4k but ~52.7 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 Mistral Small 3 24B generates at roughly ~28% of its short-context speed. How this is estimated.

Benchmark scores

Sourced third-party benchmarks for the full-precision Mistral Small 3 24B, not a specific quant. See the full leaderboard.

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) 14.33 GB
Q5_K_M 17.1 GB est
Q6_K 19.7 GB est
Q8_0 25.05 GB
FP16 48 GB est

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

Run it

Ollama
$ ollama run mistral-small3.2:24b
llama.cpp
$ llama-cli -hf bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF

Which devices can run Mistral Small 3 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 Mistral Small 3 24B need?

At Q4_K_M, Mistral Small 3 24B needs about 16.3 GB (weights ~14.33 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~27.1 GB.

What is the Q4_K_M GGUF file size of Mistral Small 3 24B?

The Q4_K_M GGUF file is about 14.33 GB to download, and the Q8_0 GGUF is about 25.05 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~16.3 GB of memory at Q4_K_M.

Can Mistral Small 3 24B run on a laptop?

Mistral Small 3 24B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Can I use Mistral Small 3 24B commercially?

Yes. Mistral Small 3 24B is licensed Apache-2.0, which permits commercial use.

Understand the numbers

Short guides to the ideas behind Mistral Small 3 24B's memory and quant figures.

Mistral Small 3.2 released June 20, 2025. Latest in the Mistral Small 3 line. Context 128K confirmed by official Mistral docs. Q4_K_M=14.33GB and Q8_0=25.05GB from bartowski HF repo (mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF). Ollama page shows 15GB for the default tag.

Sources

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