MistralCodestral 22B on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs Codestral 22B excellently at Q5_K_M — 180 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
22.2B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
Q5_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Codestral 22B on NVIDIA Grace Blackwell Ultra GB300 at Q5_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 180 tok/s | 65ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
High quality coding model. 273GB headroom.
About Codestral 22B
Codestral 22B (22.2B) is a coding, ai coding, ai building model. Mistral's dedicated coding model. Built for code completion and generation across 80+ languages. Fits on a single 16 GB GPU at Q3/Q4. Non-production license limits commercial use.
View all Codestral 22B hardware options →About NVIDIA Grace Blackwell Ultra GB300
NVIDIA Grace Blackwell Ultra GB300 has 288 GB at 8000 GB/s. Street price: $30,000.
See all models NVIDIA Grace Blackwell Ultra GB300 can run →Estimate method: Estimated from GB300 bandwidth ratio vs RTX 4090. Reference hardware source: dell.com (2026-03-23)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.