can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Qwen3 Coder Next 80B-A3B (MoE)?

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

Yes — it runs great.

Best fit: Qwen3 Coder Next 80B-A3B (MoE) at Q6_K · 65.8 GB · 204–306 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K29.2 GB259–389 tok/sRuns great
Q3_K_M38.3 GB243–364 tok/sRuns great
Q4_K_M49.3 GB226–339 tok/sRuns great
Q5_K_M59.2 GB212–318 tok/sRuns great
Q6_K65.8 GB204–306 tok/sRuns great
Q8_084.8 GB184–276 tok/sTight / slow
FP16159.5 GB132–198 tok/sWon't fit

Ran Qwen3 Coder Next 80B-A3B (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →