Mistral AI
Codestral 22B
Mistral's dedicated code generation model. Supports 80+ programming languages.
22B parametersmistralmnpl32K context14GB - 25GB VRAM
Check Your Hardware
See which quantizations of Codestral 22B your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| Q4_K_M | 4.5 | 13 GB | 14 GB | 16 GB | 85% |
| Q5_K_M | 5.5 | 15.5 GB | 16.5 GB | 20 GB | 90% |
| Q8_0 | 8 | 23.5 GB | 25 GB | 28 GB | 98% |
Frequently Asked Questions
How much VRAM do I need to run Codestral 22B?
Codestral 22B requires 14GB VRAM minimum with Q4_K_M quantization. For full precision, you need 25GB VRAM.
What is the best quantization for Codestral 22B?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.