How much VRAM does Mistral Small 4 need?

Mistral Small 4 requires 65.5 GB VRAM to run at Q4 quantization (recommended), 130.9 GB for Q8, and 261.8 GB for full FP16 precision. The minimum is 32.7 GB at Q2 with some quality loss.

What GPU do I need for Mistral Small 4?

You need at least 65.5 GB VRAM to run Mistral Small 4 at Q4 quantization. 2 consumer GPUs are compatible. The most popular choice is an NVIDIA RTX-class GPU with 65.5+ GB VRAM.

Is Mistral Small 4 free to use?

Mistral Small 4 by Mistral AI is available under the Apache 2.0 license. Check the license terms for commercial use restrictions. You can download and run it for free with Ollama: ollama run mistral-small4:latest

Local Engine Ready

Mistral Small 4

Name: Mistral Small 4
Author: Javier Morales

2 consumer GPUs can run Mistral Small 4 at Q4 natively. Precise VRAM thresholds and benchmarks below.

2 Compatible GPUs

2 with offloading

119B params

256K context

Top pick

M4 Ultra · 128 GB VRAM runs Q4 natively

Check availability See top 3 ↓

Prices and availability may change · affiliate link

Javier Morales AI hardware specialist — 8 years of experience Aktualisiert 2026-04-08

GitHub: github.com/javier-morales-ia

llama.cpp 0.2.x · CUDA 12 · ROCm 6 · updated monthly · methodology →

Execution Context

ARCHITECTURE TRANSFORMER

CONTEXT 256K TOKENS

QUANTIZATION 4-BIT GGUF

PROVIDER Mistral AI

LICENSE Apache 2.0

VRAM REQUIREMENT

65.5 GB

4GB 8GB 12GB 16GB 24GB+

Hardware Decision

This model requires aFlagship GPU (48 GB+ VRAM)

Minimum

M4 Ultra

Runs at Q4 — functional, some wait

128 GB VRAM

View compatible setup

Balanced

M3 Ultra

Best value for daily use

192 GB VRAM

View compatible setup

Optimal

M4 Ultra

Full quality, fastest inference

128 GB VRAM

View compatible setup

Compatible GPUs for Mistral Small 4

Best picks by compatibility, VRAM headroom, and value — prices and availability may change.

128 GB VRAM · Q4 native Amazon

M4 Ultra

0.0 (0 Bewertungen)

Vorteile

Runs Mistral Small 4 at Q4 natively
128 GB VRAM — adequate headroom

192 GB VRAM · Q4 native Amazon

M3 Ultra

0.0 (0 Bewertungen)

Vorteile

Runs Mistral Small 4 at Q4 natively
192 GB VRAM — adequate headroom

M3 Ultra auf Amazon ansehen →

48 GB VRAM · Offloading Amazon

M4 Max 48GB

0.0 (0 Bewertungen)

Vorteile

Works via CPU offloading
48 GB VRAM — adequate headroom

Einige Links sind Amazon-Partnerlinks. Wir koennen ohne Mehrkosten fuer Sie eine Provision erhalten. Amazon-Cookies koennen nach Ihrem Klick bis zu 24 Stunden bestehen.

How to run this model

Check if your GPU can run Mistral Small 4 →

VRAM Calculator — instant compatibility check

M4 Ultra

128 GB · Runs Q4 natively · Check availability

*Prices and availability may change. Some links are affiliate links.

System Requirements

GPU VRAM 65.5 GB High-end GPU

System RAM 99 GB 64 GB or more

Storage 59.5 GB Q4 · SSD recommended

CPU Any modern CPU GPU required

VRAM by Quantization

Quantization	VRAM needed	Disk space	Quality
FP16 (max quality)	261.8 GB	238 GB	Maximum
Q8 (high quality)	130.9 GB	119 GB	Near-lossless
Q4 (recommended) Best balance	65.5 GB	59.5 GB	Recommended
Q2 (minimum)	32.7 GB	29.8 GB	Quality loss

Model Details

Developer	Mistral AI
Parameters	119B
Context window	256,000 tokens
License	Apache 2.0
Use cases	chat, reasoning, coding, vision
Released	2026-03

Install with Ollama

ollama run mistral-small4:latest

Hugging Face

mistralai/Mistral-Small-4-119B-2603

View on HF →

Technical Requirements

Can your GPU run Mistral Small 4?

Mistral Small 4 requires <strong class="text-primary-container">65.5 GB VRAM</strong> at Q4. 2 consumer GPUs meet this threshold. Below 8 GB or 63.5 GB you'll hit significant offload latency.

M4 Ultra (128 GB) M3 Ultra (192 GB)

32.7GB Critical min

65.5GB Optimal Q4

130.9GB High Quality Q8

261.8GB Max FP16

Hardware Performance Matrix

2 Q4 native · 2 offload

GPU Unit	VRAM	Compatibility	Est. Speed	Action
M4 Ultra	128GB	Optimal	45 tok/s	Calculate →
M3 Ultra	192GB	Optimal	38 tok/s	Calculate →
M4 Max 48GB	48GB	Offload	20 tok/s	Calculate →
M4 Max 36GB	36GB	Offload	—	Calculate →

Recommended GPUs for Mistral Small 4

Reale Benchmarks

Keine bezahlten Reviews

Redaktionelle Auswahl

Datenbasiert

Best picks by compatibility, VRAM headroom, and value — prices and availability may change.

M4 Ultra

128 GB VRAM

Q4 native

Check availability →

M3 Ultra

192 GB VRAM

Q4 native

Check availability →

M4 Max 48GB

48 GB VRAM

Offloading

Check availability →

Einige Links sind Amazon-Partnerlinks. Wir koennen ohne Mehrkosten fuer Sie eine Provision erhalten. Amazon-Cookies koennen nach Ihrem Klick bis zu 24 Stunden bestehen.

Mistral Small 4 — Compatibility guide

Mistral Small 4 with 119B parameters only runs fully in multi-GPU or server configurations. Consider distilled versions if available. The VRAM calculator can help you find compatible alternatives.

Compare GPUs for Mistral Small 4

Which GPU is worth it? Real specs and benchmarks side by side.

Compare top GPUs →

M4 Ultra vs M3 Ultra

Compatible Hardware

GPUs that run Mistral Small 4 at Q4 — sorted by AI performance score.

Reale Benchmarks

Keine bezahlten Reviews

Datenbasiert

M4 Ultra

Apple · 128 GB VRAM

Q4 OK

45 tok/s > $1000

View analysis View on Amazon →

M3 Ultra

Apple · 192 GB VRAM

Q4 OK

38 tok/s > $1000

View analysis View on Amazon →

Einige Links sind Amazon-Partnerlinks. Wir koennen ohne Mehrkosten fuer Sie eine Provision erhalten. Amazon-Cookies koennen nach Ihrem Klick bis zu 24 Stunden bestehen.

More Practical Alternatives

Similar models in the chat category with comparable VRAM footprints.

Command R+

104B params • 59GB VRAM

Cohere • CC-BY-NC-4.0

Qwen2.5 72B

72B params • 41GB VRAM

Alibaba • Apache-2.0

Llama 3.1 70B

70B params • 40GB VRAM

Meta • llama-3.1-community

Llama 3.3 70B

70B params • 42GB VRAM

Meta • llama-3-community

Not sure which GPU you need for Mistral Small 4?

The VRAM Calculator tells you exactly which quantization your hardware can handle.

Open Calculator Full Hardware Wizard