Mistral Small 3.1 24B — VRAM, Speed & Local Setup

作者： Jakub Rusinowski · 最后更新： 2025年3月17日

Model library → Mistral Small 3.1 → Mistral Small 3.1 24B

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.

Specifications

Parameters24 Billion
Context window128,000
ArchitectureDense + Vision Encoder
ProviderMistral AI
LicenceApache 2.0
Specified atQ4_K_M
System RAM32 GB
Record updated2025-03-17

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K7.8 GB9.9 GB~75 tok/s (est.)Fits comfortably
Q3_K_M10.1 GB12.2 GB~61 tok/s (est.)Fits comfortably
Q4_K_M14.2 GB16.4 GB~45 tok/s (est.)Fits comfortably
Q5_K_M16.7 GB18.9 GB~40 tok/s (est.)Fits comfortably
Q6_K19.4 GB21.5 GB~35 tok/s (est.)Fits comfortably
Q8_025.1 GB27.2 GB~4 tok/s (est.)Offloads to system RAM (slow)
F1647.2 GB49.3 GB~2 tok/s (est.)Offloads to system RAM (slow)

Want the memory numbers alone, at every quantization level and your own context length? Use the Mistral Small 3.1 24B VRAM calculator.

Buy This HardwareAMD Radeon RX 9060 XT 16GB — 16 GB VRAM · 160 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs Mistral Small 3.1 24B is the AMD Radeon RX 9060 XT 16GB (16 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。
AMD Radeon RX 9060 XT 16GB
16 GB VRAM · 160 W board power
2026年价格波动较大——请以当前商品页价格为准。
在亚马逊查看价格

How to Run Mistral Small 3.1 24B

Install Ollama, then run:

ollama run mistral-small3.1

Weights on Hugging Face: mistralai/Mistral-Small-3.1-24B-Instruct-2503.

Best for: vision, rag, chat, commercial.

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.

← All Mistral Small 3.1 models | VRAM calculator | Build a PC for this model | Check your own hardware