Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Qwen3.5 9B?
Qwen · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.5 9B at FP16 · 17.9 GB · 128–192 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 3.9 GB | 254–381 tok/s | Runs great |
| Q4_K_M | 5.4 GB | 229–343 tok/s | Runs great |
| Q5_K_M | 6.4 GB | 216–324 tok/s | Runs great |
| Q6_K | 7.4 GB | 203–305 tok/s | Runs great |
| Q8_0 | 9.5 GB | 182–273 tok/s | Runs great |
| FP16 | 17.9 GB | 128–192 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsQwen3.5 9B on other machinesWhat to buy to run it →
Ran Qwen3.5 9B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →