can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run GLM-5.2 (MoE)?

GLM · MIT · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-5.2 (MoE) at Q5_K_M · 560.8 GB · 20–30 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M342.7 GB57–86 tok/sRuns great
Q4_K_M465.8 GB28–42 tok/sRuns great
Q5_K_M560.8 GB20–30 tok/sRuns great
Q6_K625.9 GB17–25 tok/sTight / slow
Q8_0801.4 GB12–17 tok/sWon't fit
FP161508.0 GB5–8 tok/sWon't fit

Ran GLM-5.2 (MoE) on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →