can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M2 Ultra (192GB) run GLM-4 9B?

GLM · MIT · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 24–37 tok/s on a Mac Studio M2 Ultra (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB74–111 tok/sRuns great
Q3_K_M5.0 GB65–98 tok/sRuns great
Q4_K_M6.2 GB57–85 tok/sRuns great
Q5_K_M7.1 GB52–78 tok/sRuns great
Q6_K8.3 GB47–70 tok/sRuns great
Q8_010.0 GB41–61 tok/sRuns great
FP1618.8 GB24–37 tok/sRuns great

Ran GLM-4 9B on a Mac Studio M2 Ultra (192GB)? Add your real numbers →