Mistral AI22B~14 GB VRAM at Q4_K_M

Codestral 22B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

The best local model for IDE integration. Trained on 80+ programming languages with Fill-In-Middle support for autocomplete. Use with continue.dev or Cursor for production-grade code assistance. Fits in 16GB VRAM.

Codestral 22B needs about 14 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.

Logic88
Creative55
Coding97

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
10 GB~76 tok/sFits
Q3_K_M
3.41 bpw
12.1 GB~62 tok/sFits
Q4_K_M
4.83 bpw
16.1 GB~47 tok/sFits
Q5_K_M
5.67 bpw
18.4 GB~41 tok/sFits
Q6_K
6.56 bpw
20.9 GB~36 tok/sFits
Q8_0
8.50 bpw
26.3 GB~4 tok/sOffload
F16
16.00 bpw
47.1 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. Codestral 22B VRAM calculator →

Get Codestral 22B running

The cheapest catalogued GPU that runs Codestral 22B is the AMD Radeon RX 9060 XT 16GB (16 GB).

Buy this hardware AMD Radeon RX 9060 XT 16GB — 16 GB VRAM · 160 W board powerDeploy in the cloud now RTX 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.

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 9060 XT 16GB
16 GB VRAM · 160 W board power
2026 prices are volatile — check the current listing.

How to run Codestral 22B

Install Ollama, then run:

ollama run codestral:22b
Weights on Hugging Face: mistralai/Codestral-22B-v0.1 ↗

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
22 Billion
Context window
32,768
Architecture
Dense
Provider
Mistral AI
Licence
MNPL (Non-Commercial)
Practical deployment
Laptop
Specified at
Q4_K_M
System RAM
24 GB
Record updated
2024-05-29
LicenceMNPL-0.1Research / non-commercial only

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

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 forcoding agentide plugincode completiondev work

Can I run Codestral 22B on my GPU?

Codestral 22B — frequently asked questions

How much VRAM does Codestral 22B need?

About 14 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 Codestral 22B run on an RTX 4090 (24 GB)?

Yes. Codestral 22B needs about 14 GB at Q4_K_M, inside a 24 GB card, at an estimated 47 tokens/sec.

How do I run Codestral 22B locally?

Install Ollama and run `ollama run codestral:22b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.