can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (128GB) run GLM-4.5 Air (MoE)?

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

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q4_K_M · 73.0 GB · 37–56 tok/s on a MacBook Pro M5 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB51–76 tok/sRuns great
Q3_K_M57.2 GB44–66 tok/sRuns great
Q4_K_M73.0 GB37–56 tok/sRuns great
Q5_K_M83.5 GB34–51 tok/sTight / slow
Q6_K99.0 GB30–45 tok/sWon't fit
Q8_0117.5 GB26–39 tok/sWon't fit
FP16221.0 GB15–23 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a MacBook Pro M5 Max (128GB)? Add your real numbers →