Codestral 22B on NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 runs Codestral 22B excellently at 35 tok/s at Q5_K_M. This is a strong pairing.
Model Size
22.2B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Codestral 22B performance at a different quality level on NVIDIA GeForce RTX 4090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 35 tok/s | 220ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
Q5 at 15.1GB on 4090. Fast and high quality. 8.9GB headroom for embeddings.
About Codestral 22B
Codestral 22B (22.2B) is a coding, ai coding, ai building model. Mistral's dedicated coding model. Strong at code completion and generation across 80+ languages. Fits on a single 16GB GPU at Q3/Q4. Non-production license limits commercial use.
View all Codestral 22B hardware options →About NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Source: Community benchmarks (2026-01-15)
Data last updated: 2026-03-01