Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Qwen3 14B?
Qwen · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 14B at FP16 · 29.5 GB · 90–135 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 5.8 GB | 222–333 tok/s | Runs great |
| Q3_K_M | 7.3 GB | 203–304 tok/s | Runs great |
| Q4_K_M | 9.0 GB | 185–278 tok/s | Runs great |
| Q5_K_M | 10.5 GB | 172–258 tok/s | Runs great |
| Q6_K | 12.1 GB | 160–240 tok/s | Runs great |
| Q8_0 | 15.7 GB | 138–207 tok/s | Runs great |
| FP16 | 29.5 GB | 90–135 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsQwen3 14B on other machinesWhat to buy to run it →
Ran Qwen3 14B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →