can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (256GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 256.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at FP16 · 59.9 GB · 75–112 tok/s on a Mac Studio M5 Ultra (256GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.3 GB134–201 tok/sRuns great
Q3_K_M14.6 GB127–191 tok/sRuns great
Q4_K_M18.3 GB120–181 tok/sRuns great
Q5_K_M21.4 GB115–173 tok/sRuns great
Q6_K24.7 GB110–165 tok/sRuns great
Q8_031.8 GB101–151 tok/sRuns great
FP1659.9 GB75–112 tok/sRuns great

Ran GLM-4.7 Flash (MoE) on a Mac Studio M5 Ultra (256GB)? Add your real numbers →