can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Qwen3 8B?

Qwen · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Qwen3 8B at FP16 · 16.4 GB · 135–202 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.3 GB263–395 tok/sRuns great
Q3_K_M4.1 GB248–372 tok/sRuns great
Q4_K_M5.0 GB234–350 tok/sRuns great
Q5_K_M5.9 GB222–333 tok/sRuns great
Q6_K6.7 GB210–316 tok/sRuns great
Q8_08.7 GB189–283 tok/sRuns great
FP1616.4 GB135–202 tok/sRuns great

Ran Qwen3 8B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →