Can I run this LLM?
Can a NVIDIA H200 (141GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 141.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 27B at FP16 · 54.7 GB · 55–82 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 10.8 GB | 171–256 tok/s | Runs great |
| Q3_K_M | 13.4 GB | 152–228 tok/s | Runs great |
| Q4_K_M | 17.4 GB | 129–194 tok/s | Runs great |
| Q5_K_M | 20.9 GB | 115–172 tok/s | Runs great |
| Q6_K | 23.9 GB | 105–157 tok/s | Runs great |
| Q8_0 | 29.1 GB | 91–136 tok/s | Runs great |
| FP16 | 54.7 GB | 55–82 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a NVIDIA H200 (141GB)? Add your real numbers →