can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Hunyuan Hy3 (MoE)?

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

Yes — it runs great.

Best fit: Hunyuan Hy3 (MoE) at Q8_0 · 317.7 GB · 19–28 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K106.7 GB193–290 tok/sRuns great
Q3_K_M137.6 GB124–186 tok/sRuns great
Q4_K_M182.2 GB52–78 tok/sRuns great
Q5_K_M212.8 GB37–56 tok/sRuns great
Q6_K257.3 GB26–40 tok/sRuns great
Q8_0317.7 GB19–28 tok/sRuns great

Ran Hunyuan Hy3 (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →