Back to Quant Hub

Codestral 22B

22B

Mistral AI

Mistral's dedicated code model. 80+ language support, Fill-in-the-Middle capable.

⬇ 4.5K HF downloads♥ 194 likesbartowski/Codestral-22B-v0.1-GGUF· stats from 6/24/2026
Consumer GPUPro GPU

33K

Max Context

2

Quant Variants

GGUF Q4_K_M

Best Quality

97.0%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

FormatLevelBPWVRAMPPL LossSpeedActions
GGUFQ4_K_M4.8514.8 GB3.0%58 tok/s
CalcHF
AWQINT4413.2 GB4.2%72 tok/s
CalcHF