can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (96GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at Q8_0 · 31.8 GB · 81–121 tok/s on a Mac Studio M3 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.3 GB116–174 tok/sRuns great
Q3_K_M14.6 GB108–162 tok/sRuns great
Q4_K_M18.3 GB101–151 tok/sRuns great
Q5_K_M21.4 GB96–143 tok/sRuns great
Q6_K24.7 GB90–136 tok/sRuns great
Q8_031.8 GB81–121 tok/sRuns great
FP1659.9 GB57–86 tok/sTight / slow

Ran GLM-4.7 Flash (MoE) on a Mac Studio M3 Ultra (96GB)? Add your real numbers →