can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Qwen3.8 27B?

Qwen · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3.8 27B at FP16 · 54.6 GB · 22–33 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M11.8 GB80–120 tok/sRuns great
Q4_K_M16.6 GB62–93 tok/sRuns great
Q5_K_M19.5 GB55–82 tok/sRuns great
Q6_K22.5 GB49–73 tok/sRuns great
Q8_029.0 GB39–59 tok/sRuns great
FP1654.6 GB22–33 tok/sRuns great

Ran Qwen3.8 27B on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →