Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Qwen3.6 35B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 35B-A3B (MoE) at FP16 · 69.4 GB · 223–335 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 16.6 GB | 311–467 tok/s | Runs great |
| Q4_K_M | 22.1 GB | 299–448 tok/s | Runs great |
| Q5_K_M | 26.5 GB | 290–435 tok/s | Runs great |
| Q6_K | 29.3 GB | 284–426 tok/s | Runs great |
| Q8_0 | 36.9 GB | 270–405 tok/s | Runs great |
| FP16 | 69.4 GB | 223–335 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3.6 35B-A3B (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →