can-i-run-this-llm

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

QuantSizeSpeedFit
Q3_K_M11.6 GB205–308 tok/sRuns great
Q4_K_M16.3 GB176–265 tok/sRuns great
Q5_K_M19.2 GB163–244 tok/sRuns great
Q6_K22.2 GB150–225 tok/sRuns great
Q8_028.6 GB129–194 tok/sRuns great
FP1653.8 GB83–125 tok/sRuns great

Ran Qwen3.6 27B on a NVIDIA B200 (192GB)? Add your real numbers →