LocalOps LogoLocalOps
Back to Calculator

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

Source
ArchitectureTEXT
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.

Deploy Now

Quantization Estimates

FormatVRAM NeedTier
FP1644.0 GBFull Precision
Q8_022.0 GBHigh
Q6_K18.7 GBExcellent
Q5_K_M15.4 GBGreat
Q4_K_M11.0 GBSweet Spot
Q2_K6.6 GBEmergency

Share this Model

Send these specs directly to your community.

Post