can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (96GB) run GLM-4 9B?

GLM · MIT · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at FP16 · 18.8 GB · 35–52 tok/s on a Mac Studio M5 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB92–138 tok/sRuns great
Q3_K_M5.0 GB83–125 tok/sRuns great
Q4_K_M6.2 GB74–111 tok/sRuns great
Q5_K_M7.1 GB69–103 tok/sRuns great
Q6_K8.3 GB62–94 tok/sRuns great
Q8_010.0 GB55–83 tok/sRuns great
FP1618.8 GB35–52 tok/sRuns great

Ran GLM-4 9B on a Mac Studio M5 Ultra (96GB)? Add your real numbers →