can-i-run-this-llm

Can I run this LLM?

Can a Mac mini M6 (24GB) run GLM-4 9B?

GLM · MIT · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at Q6_K · 8.3 GB · 13–19 tok/s on a Mac mini M6 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB24–35 tok/sRuns great
Q3_K_M5.0 GB20–30 tok/sRuns great
Q4_K_M6.2 GB16–25 tok/sRuns great
Q5_K_M7.1 GB15–22 tok/sRuns great
Q6_K8.3 GB13–19 tok/sRuns great
Q8_010.0 GB11–16 tok/sTight / slow
FP1618.8 GB6–9 tok/sWon't fit

Ran GLM-4 9B on a Mac mini M6 (24GB)? Add your real numbers →