can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M1 Pro (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 Q6_K · 7.8 GB · 15–23 tok/s on a MacBook Pro M1 Pro (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB34–50 tok/sRuns great
Q3_K_M4.1 GB27–40 tok/sRuns great
Q4_K_M5.7 GB20–30 tok/sRuns great
Q5_K_M6.7 GB18–26 tok/sRuns great
Q6_K7.8 GB15–23 tok/sRuns great
Q8_010.0 GB12–18 tok/sTight / slow
FP1618.8 GB7–10 tok/sWon't fit

Ran GLM-4 9B on a MacBook Pro M1 Pro (16GB)? Add your real numbers →