Ministral 8B — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated October 16, 2024

Model library → Ministral → Ministral 8B

The best lightweight Mistral model. Outstanding reasoning scores for 8B size. Works on 6 GB VRAM cards (RTX 3060, RTX 4060, RX 7600). Very fast at 60–90 tokens/sec.

Ministral 8B needs about 6 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

Parameters8 Billion
Context window32,768
ArchitectureDense, Decoder-only
ProviderMistral AI
LicenceMistral Research
Specified atQ4_K_M
System RAM16 GB
Record updated2024-10-16

Licence

Mistral Research — research / non-commercial only. Research / non-commercial only — this licence does NOT permit shipping a commercial product.

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_K2.6 GB4.6 GB~153 tok/s (est.)Fits comfortably
Q3_K_M3.4 GB5.4 GB~132 tok/s (est.)Fits comfortably
Q4_K_M4.8 GB6.9 GB~106 tok/s (est.)Fits comfortably
Q5_K_M5.7 GB7.7 GB~95 tok/s (est.)Fits comfortably
Q6_K6.6 GB8.6 GB~85 tok/s (est.)Fits comfortably
Q8_08.5 GB10.5 GB~70 tok/s (est.)Fits comfortably
F1616.0 GB18.0 GB~41 tok/s (est.)Fits comfortably

Want the memory numbers alone, at every quantization level and your own context length? Use the Ministral 8B VRAM calculator.

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 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 Ministral 8B is the Intel Arc B570 (10 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.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run Ministral 8B

Install Ollama, then run:

ollama run ministral:8b

Weights on Hugging Face: mistralai/Ministral-8B-Instruct-2410.

Best for: chat, coding, reasoning, rag.

Can I Run Ministral 8B on My GPU?

Other Ministral Sizes

Ministral 8B — Frequently Asked Questions

How much VRAM does Ministral 8B need?
About 6 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 Ministral 8B run on an RTX 4090 (24 GB)?
Yes. Ministral 8B needs about 6 GB at Q4_K_M, inside a 24 GB card, at an estimated 106 tokens/sec.
How do I run Ministral 8B locally?
Install Ollama and run `ollama run ministral:8b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Ministral come in?
Ministral 3B (3 GB), Ministral 8B (6 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Ministral models | VRAM calculator | Check your own hardware