can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Qwen3.6 35B-A3B (MoE)?

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

Yes — it runs great.

Best fit: Qwen3.6 35B-A3B (MoE) at FP16 · 69.3 GB · 133–200 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M14.9 GB253–379 tok/sRuns great
Q4_K_M21.0 GB230–345 tok/sRuns great
Q5_K_M24.7 GB218–327 tok/sRuns great
Q6_K28.6 GB206–309 tok/sRuns great
Q8_036.8 GB186–278 tok/sRuns great
FP1669.3 GB133–200 tok/sRuns great

Ran Qwen3.6 35B-A3B (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →