Back to CalculatorDeploy Now
Codestral 2 (22B)
Mistral Apr 2026; next-gen code specialist, FIM support, beats GPT-4o on HumanEval and MBPP. First Codestral under Apache 2.0 — previous versions were non-commercial MNPL.
Specifications
SourceArchitectureTEXT
Parameters22B
Familycodestral
VRAM (Q4)11.0G
Apache 2.0 licensed. 256K context. 380K HF downloads in first week. Runs on single RTX 4090 at Q4 (~13GB VRAM).
mistralcodingfimapache2open-sourceide
Build your Local Rig
Ready to run locally? Shop top-tier GPUs on Amazon for the best performance.
Instant Cloud GPUs
Running out of VRAM? Rent a high-end H100 or RTX 4090 on RunPod and deploy in seconds.
Quantization Estimates
| Format | VRAM Need | Tier |
|---|---|---|
| FP16 | 44.0 GB | Full Precision |
| Q8_0 | 22.0 GB | High |
| Q6_K | 18.7 GB | Excellent |
| Q5_K_M | 15.4 GB | Great |
| Q4_K_M | 11.0 GB | Sweet Spot |
| Q2_K | 6.6 GB | Emergency |
Share this Model
Send these specs directly to your community.