Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Mistral Small 3.2 24B?
Mistral · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Mistral Small 3.2 24B at FP16 · 47.2 GB · 63–94 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 8.9 GB | 186–279 tok/s | Runs great |
| Q3_K_M | 11.5 GB | 164–247 tok/s | Runs great |
| Q4_K_M | 14.3 GB | 146–218 tok/s | Runs great |
| Q5_K_M | 16.8 GB | 133–199 tok/s | Runs great |
| Q6_K | 19.4 GB | 121–182 tok/s | Runs great |
| Q8_0 | 25.1 GB | 102–153 tok/s | Runs great |
| FP16 | 47.2 GB | 63–94 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsMistral Small 3.2 24B on other machinesWhat to buy to run it →
Ran Mistral Small 3.2 24B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →