Ministral 3B — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated October 16, 2024

Model library → Ministral → Ministral 3B

Ultra-lightweight Mistral model for phones and edge devices. 2 GB VRAM required — even runs on integrated graphics.

Ministral 3B needs about 3 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

Parameters3 Billion
Context window32,768
ArchitectureDense, Decoder-only
ProviderMistral AI
LicenceMistral Research
Specified atQ4_K_M
System RAM8 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), with no KV cache (this record has no published architecture). 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_K1.2 GB2.0 GB~228 tok/s (est.)Fits comfortably
Q3_K_M1.5 GB2.3 GB~206 tok/s (est.)Fits comfortably
Q4_K_M2.2 GB3.0 GB~176 tok/s (est.)Fits comfortably
Q5_K_M2.6 GB3.4 GB~161 tok/s (est.)Fits comfortably
Q6_K3.0 GB3.8 GB~149 tok/s (est.)Fits comfortably
Q8_03.8 GB4.6 GB~127 tok/s (est.)Fits comfortably
F167.2 GB8.0 GB~81 tok/s (est.)Fits comfortably

Want the memory numbers alone, at every quantization level and your own context length? Use the Ministral 3B 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 3B 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 3B

Install Ollama, then run:

ollama run ministral:3b

Weights on Hugging Face: mistralai/Ministral-3B-Instruct-2410.

Best for: phone, edge devices, chat, quick tasks.

Can I Run Ministral 3B on My GPU?

Other Ministral Sizes

Ministral 3B — Frequently Asked Questions

How much VRAM does Ministral 3B need?
About 3 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 3B run on an RTX 4090 (24 GB)?
Yes. Ministral 3B needs about 3 GB at Q4_K_M, inside a 24 GB card, at an estimated 176 tokens/sec.
How do I run Ministral 3B locally?
Install Ollama and run `ollama run ministral:3b`. 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