can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M2 Ultra (192GB) run GLM-4.5 Air (MoE)?

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

Yes — it runs great.

Best fit: GLM-4.5 Air (MoE) at Q8_0 · 117.5 GB · 32–48 tok/s on a Mac Studio M2 Ultra (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.3 GB61–91 tok/sRuns great
Q3_K_M57.2 GB53–80 tok/sRuns great
Q4_K_M73.0 GB46–68 tok/sRuns great
Q5_K_M83.5 GB41–62 tok/sRuns great
Q6_K99.0 GB37–55 tok/sRuns great
Q8_0117.5 GB32–48 tok/sRuns great
FP16221.0 GB19–29 tok/sWon't fit

Ran GLM-4.5 Air (MoE) on a Mac Studio M2 Ultra (192GB)? Add your real numbers →