Mistral AI24B~15 GB VRAM at Q4_K_M

Mistral Small 3.1 24B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

The best Apache 2.0 licensed model in the 24B class — can see images, has 128k context, and outperforms Gemma 3 27B on most benchmarks. Ideal for commercial deployment where licensing matters.

Mistral Small 3.1 24B needs about 15 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic92
Creative89
Coding90

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
9.9 GB~75 tok/sFits
Q3_K_M
3.41 bpw
12.2 GB~61 tok/sFits
Q4_K_M
4.83 bpw
16.4 GB~45 tok/sFits
Q5_K_M
5.67 bpw
18.9 GB~40 tok/sFits
Q6_K
6.56 bpw
21.5 GB~35 tok/sFits
Q8_0
8.50 bpw
27.2 GB~4 tok/sOffload
F16
16.00 bpw
49.3 GB~2 tok/sOffload

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Mistral Small 3.1 24B VRAM calculator →

Get Mistral Small 3.1 24B running

The cheapest catalogued GPU that runs Mistral Small 3.1 24B is the AMD Radeon RX 7900 XT (20 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
2026 prices are volatile — check the current listing.

How to run Mistral Small 3.1 24B

Install Ollama, then run:

ollama run mistral-small3.1

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters
24 Billion
Context window
128,000
Architecture
Dense + Vision Encoder
Provider
Mistral AI
Licence
Apache 2.0
Practical deployment
Single consumer GPU
Specified at
Q4_K_M
System RAM
32 GB
Record updated
2025-03-17
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forvisionragchatcommercial

Can I run Mistral Small 3.1 24B on my GPU?

Mistral Small 3.1 24B — frequently asked questions

How much VRAM does Mistral Small 3.1 24B need?

About 15 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Mistral Small 3.1 24B run on an RTX 4090 (24 GB)?

Yes. Mistral Small 3.1 24B needs about 15 GB at Q4_K_M, inside a 24 GB card, at an estimated 45 tokens/sec.

How do I run Mistral Small 3.1 24B locally?

Install Ollama and run `ollama run mistral-small3.1`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.