can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run GLM-5.3 Flash (MoE)?

GLM · MIT · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-5.3 Flash (MoE) at Q8_0 · 341.5 GB · 21–32 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K125.7 GB213–319 tok/sRuns great
Q3_K_M155.0 GB100–151 tok/sRuns great
Q4_K_M200.8 GB53–79 tok/sRuns great
Q5_K_M243.7 GB36–55 tok/sRuns great
Q6_K281.0 GB29–43 tok/sRuns great
Q8_0341.5 GB21–32 tok/sRuns great

Ran GLM-5.3 Flash (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →