can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Pro (36GB) run GLM-4 9B?

GLM · MIT · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at Q5_K_M · 6.7 GB · 14–20 tok/s on a MacBook Pro M3 Pro (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB27–40 tok/sRuns great
Q3_K_M4.1 GB21–32 tok/sRuns great
Q4_K_M5.7 GB16–24 tok/sRuns great
Q5_K_M6.7 GB14–20 tok/sRuns great
Q6_K7.8 GB12–18 tok/sTight / slow
Q8_010.0 GB9–14 tok/sTight / slow
FP1618.8 GB5–8 tok/sTight / slow

Ran GLM-4 9B on a MacBook Pro M3 Pro (36GB)? Add your real numbers →