can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M1 Max (64GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at Q8_0 · 31.8 GB · 52–78 tok/s on a MacBook Pro M1 Max (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K9.7 GB90–135 tok/sRuns great
Q3_K_M12.9 GB82–122 tok/sRuns great
Q4_K_M18.2 GB70–106 tok/sRuns great
Q5_K_M21.3 GB65–97 tok/sRuns great
Q6_K24.7 GB60–90 tok/sRuns great
Q8_031.8 GB52–78 tok/sRuns great
FP1659.9 GB34–50 tok/sWon't fit

Ran GLM-4.7 Flash (MoE) on a MacBook Pro M1 Max (64GB)? Add your real numbers →