Can I run this LLM?
Can a NVIDIA H200 (141GB) run Qwen3 30B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 141.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 30B-A3B (MoE) at FP16 · 61.1 GB · 221–331 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 9.9 GB | 321–482 tok/s | Runs great |
| Q3_K_M | 13.2 GB | 312–468 tok/s | Runs great |
| Q4_K_M | 18.5 GB | 298–448 tok/s | Runs great |
| Q5_K_M | 21.8 GB | 291–436 tok/s | Runs great |
| Q6_K | 25.2 GB | 283–424 tok/s | Runs great |
| Q8_0 | 32.4 GB | 268–401 tok/s | Runs great |
| FP16 | 61.1 GB | 221–331 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsQwen3 30B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3 30B-A3B (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →