can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Qwen3.8 Flash Next?

Qwen · See model card · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3.8 Flash Next at Q8_0 · 188.2 GB · 75–112 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q8_0188.2 GB75–112 tok/sRuns great
FP16354.0 GB8–12 tok/sTight / slow
Open the full calculator →Everything a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) runsQwen3.8 Flash Next on other machinesWhat to buy to run it →

Ran Qwen3.8 Flash Next on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →