can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Qwen3.8 Flash Next (MoE)?

Qwen · See model card · estimated for a 96.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Qwen3.8 Flash Next (MoE) at Q2_K · 80.9 GB · 205–307 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K80.9 GB205–307 tok/sTight / slow
Q3_K_M92.0 GB194–290 tok/sWon't fit
Q4_K_M119.6 GB170–255 tok/sWon't fit
Q5_K_M134.7 GB160–240 tok/sWon't fit
Q6_K168.1 GB141–211 tok/sWon't fit
Q8_0188.3 GB131–197 tok/sWon't fit
FP16354.0 GB84–126 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX Pro 6000 Blackwell (96GB) runsQwen3.8 Flash Next (MoE) on other machinesWhat to buy to run it →

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