Skip to content

Text model · Mistral

Ministral 3 8B: RAM and VRAM requirements

Ministral 3 8B needs about 6.3 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~4.84 GB to download; KV cache and overhead add the rest), or about 9.9 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 3060 Ti (8GB).

Mistral family · 8B params · released Dec 2025 · 1.4M Ollama pulls.

Shopping for hardware? See what runs Ministral 3 8B →

License Apache-2.0 · Commercial OK ↓ 121.9K/mo ♥ 200 on HuggingFace
Q4_K_M GGUF
4.84 GB
Q8_0 GGUF
8.41 GB
Memory @ Q4 (4k)
~6.3 GB
Context
256 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?

Ministral 3 8B runs on 35 of 43 tracked devices at Q4_K_M.

33 run well 2 tight fit 8 too small
Fit check Q4_K_M
Yes, it runs fast
needs 6.3 GB usable 10.5 GB
See the full breakdown
$ollama run ministral-3:8b

Memory breakdown

Weights (Q4_K_M)4.84 GB
+
KV cache (4k)0.7 GB
+
Overhead0.8 GB
=
Total6.3 GB

How context length changes it

4k context ~6.3 GB 32k context ~11 GB 128k context ~27.3 GB

Longer context grows the KV cache quickly: Ministral 3 8B needs ~6.3 GB at 4k but ~27.3 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 Ministral 3 8B generates at roughly ~18% of its short-context speed. How this is estimated.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 3.4 GB est
Q3_K_M 3.9 GB est
Q4_K_M (default) 4.84 GB
Q5_K_M 5.7 GB est
Q6_K 6.6 GB est
Q8_0 8.41 GB
FP16 17.85 GB

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

Run it

Ollama
$ ollama run ministral-3:8b
llama.cpp
$ llama-cli -hf mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
LM Studio
$ lms get mistralai/Ministral-3-8B-Instruct-2512-GGUF

Which devices can run Ministral 3 8B?

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 Ministral 3 8B need?

At Q4_K_M, Ministral 3 8B needs about 6.3 GB (weights ~4.84 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~9.9 GB.

What is the Q4_K_M GGUF file size of Ministral 3 8B?

The Q4_K_M GGUF file is about 4.84 GB to download, and the Q8_0 GGUF is about 8.41 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~6.3 GB of memory at Q4_K_M.

Can Ministral 3 8B run on a laptop?

Yes, Ministral 3 8B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use Ministral 3 8B commercially?

Yes. Ministral 3 8B is licensed Apache-2.0, which permits commercial use.

Understand the numbers

Short guides to the ideas behind Ministral 3 8B's memory and quant figures.

Mid size of Mistral's edge family: dense 8B with vision, 256K context, Apache-2.0. Sizes from Mistral's own GGUF repo.

Sources

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