can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M5 (16GB) run GLM-4 9B?

GLM · MIT · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at Q5_K_M · 7.1 GB · 13–20 tok/s on a MacBook Air/Pro M5 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB22–32 tok/sRuns great
Q3_K_M5.0 GB18–27 tok/sRuns great
Q4_K_M6.2 GB15–22 tok/sRuns great
Q5_K_M7.1 GB13–20 tok/sRuns great
Q6_K8.3 GB11–17 tok/sTight / slow
Q8_010.0 GB10–14 tok/sTight / slow
FP1618.8 GB5–8 tok/sWon't fit

Ran GLM-4 9B on a MacBook Air/Pro M5 (16GB)? Add your real numbers →