can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Max (64GB) run GLM-4 9B?

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

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 13–20 tok/s on a MacBook Pro M3 Max (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB56–84 tok/sRuns great
Q3_K_M4.1 GB47–70 tok/sRuns great
Q4_K_M5.7 GB36–54 tok/sRuns great
Q5_K_M6.7 GB32–48 tok/sRuns great
Q6_K7.8 GB28–43 tok/sRuns great
Q8_010.0 GB23–35 tok/sRuns great
FP1618.8 GB13–20 tok/sRuns great

Ran GLM-4 9B on a MacBook Pro M3 Max (64GB)? Add your real numbers →