can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Max (48GB) run GLM-4 9B?

GLM · MIT · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 17–26 tok/s on a MacBook Pro M4 Max (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB69–103 tok/sRuns great
Q3_K_M4.1 GB58–87 tok/sRuns great
Q4_K_M5.7 GB46–69 tok/sRuns great
Q5_K_M6.7 GB41–61 tok/sRuns great
Q6_K7.8 GB37–55 tok/sRuns great
Q8_010.0 GB30–45 tok/sRuns great
FP1618.8 GB17–26 tok/sRuns great

Ran GLM-4 9B on a MacBook Pro M4 Max (48GB)? Add your real numbers →