can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run GLM-5.3 Flash (MoE)?

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

Yes — it runs great.

Best fit: GLM-5.3 Flash (MoE) at Q8_0 · 341.5 GB · 46–69 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K125.7 GB254–381 tok/sRuns great
Q3_K_M155.0 GB237–356 tok/sRuns great
Q4_K_M200.8 GB215–323 tok/sRuns great
Q5_K_M243.7 GB198–297 tok/sRuns great
Q6_K281.0 GB103–155 tok/sRuns great
Q8_0341.5 GB46–69 tok/sRuns great

Ran GLM-5.3 Flash (MoE) on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →