can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (128GB) run GLM-4 9B?

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

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 19–29 tok/s on a MacBook Pro M5 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB63–94 tok/sRuns great
Q3_K_M5.0 GB55–82 tok/sRuns great
Q4_K_M6.2 GB47–71 tok/sRuns great
Q5_K_M7.1 GB43–65 tok/sRuns great
Q6_K8.3 GB38–57 tok/sRuns great
Q8_010.0 GB33–49 tok/sRuns great
FP1618.8 GB19–29 tok/sRuns great

Ran GLM-4 9B on a MacBook Pro M5 Max (128GB)? Add your real numbers →