can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (512GB) run GLM-4 9B?

GLM · MIT · estimated for a 512.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 25–37 tok/s on a Mac Studio M3 Ultra (512GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB75–112 tok/sRuns great
Q3_K_M5.0 GB66–99 tok/sRuns great
Q4_K_M6.2 GB58–87 tok/sRuns great
Q5_K_M7.1 GB53–79 tok/sRuns great
Q6_K8.3 GB47–71 tok/sRuns great
Q8_010.0 GB41–62 tok/sRuns great
FP1618.8 GB25–37 tok/sRuns great

Ran GLM-4 9B on a Mac Studio M3 Ultra (512GB)? Add your real numbers →