Can I run this LLM?
Can a NVIDIA B200 (192GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 27B at FP16 · 53.8 GB · 83–125 tok/s on a NVIDIA B200 (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 11.6 GB | 205–308 tok/s | Runs great |
| Q4_K_M | 16.3 GB | 176–265 tok/s | Runs great |
| Q5_K_M | 19.2 GB | 163–244 tok/s | Runs great |
| Q6_K | 22.2 GB | 150–225 tok/s | Runs great |
| Q8_0 | 28.6 GB | 129–194 tok/s | Runs great |
| FP16 | 53.8 GB | 83–125 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA B200 (192GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a NVIDIA B200 (192GB)? Add your real numbers →