can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (512GB) run GLM-5.3 Flash (MoE)?

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

Yes — it runs great.

Best fit: GLM-5.3 Flash (MoE) at Q6_K · 281.0 GB · 40–60 tok/s on a Mac Studio M5 Ultra (512GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K125.7 GB69–104 tok/sRuns great
Q3_K_M155.0 GB61–91 tok/sRuns great
Q4_K_M200.8 GB51–77 tok/sRuns great
Q5_K_M243.7 GB45–67 tok/sRuns great
Q6_K281.0 GB40–60 tok/sRuns great
Q8_0341.5 GB34–52 tok/sTight / slow

Ran GLM-5.3 Flash (MoE) on a Mac Studio M5 Ultra (512GB)? Add your real numbers →