can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Pro (48GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at Q6_K · 24.7 GB · 46–70 tok/s on a MacBook Pro M4 Pro (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.3 GB70–105 tok/sRuns great
Q3_K_M14.6 GB62–93 tok/sRuns great
Q4_K_M18.3 GB55–83 tok/sRuns great
Q5_K_M21.4 GB51–76 tok/sRuns great
Q6_K24.7 GB46–70 tok/sRuns great
Q8_031.8 GB39–59 tok/sTight / slow
FP1659.9 GB25–37 tok/sWon't fit

Ran GLM-4.7 Flash (MoE) on a MacBook Pro M4 Pro (48GB)? Add your real numbers →