can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M2 Max (96GB) run GLM-4.5 Air (MoE)?

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

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q3_K_M · 57.2 GB · 31–47 tok/s on a MacBook Pro M2 Max (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB37–56 tok/sRuns great
Q3_K_M57.2 GB31–47 tok/sRuns great
Q4_K_M73.0 GB26–39 tok/sWon't fit
Q5_K_M83.5 GB24–35 tok/sWon't fit
Q6_K99.0 GB21–31 tok/sWon't fit
Q8_0117.5 GB18–27 tok/sWon't fit
FP16221.0 GB10–15 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a MacBook Pro M2 Max (96GB)? Add your real numbers →