can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (128GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at FP16 · 59.9 GB · 56–84 tok/s on a Mac Studio M1 Ultra (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K9.7 GB118–177 tok/sRuns great
Q3_K_M12.9 GB111–166 tok/sRuns great
Q4_K_M18.2 GB100–150 tok/sRuns great
Q5_K_M21.3 GB94–141 tok/sRuns great
Q6_K24.7 GB89–134 tok/sRuns great
Q8_031.8 GB80–119 tok/sRuns great
FP1659.9 GB56–84 tok/sRuns great

Ran GLM-4.7 Flash (MoE) on a Mac Studio M1 Ultra (128GB)? Add your real numbers →