Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Qwen3 Coder Next 80B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 Coder Next 80B-A3B (MoE) at FP16 · 159.5 GB · 121–181 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 29.2 GB | 318–478 tok/s | Runs great |
| Q3_K_M | 38.3 GB | 309–464 tok/s | Runs great |
| Q4_K_M | 49.3 GB | 299–448 tok/s | Runs great |
| Q5_K_M | 59.2 GB | 290–434 tok/s | Runs great |
| Q6_K | 65.8 GB | 284–426 tok/s | Runs great |
| Q8_0 | 84.8 GB | 269–403 tok/s | Runs great |
| FP16 | 159.5 GB | 121–181 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsQwen3 Coder Next 80B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3 Coder Next 80B-A3B (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →