can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (512GB) run GLM-5.2 (MoE)?

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

Yes — it runs great.

Best fit: GLM-5.2 (MoE) at Q2_K · 253.9 GB · 32–48 tok/s on a Mac Studio M3 Ultra (512GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K253.9 GB32–48 tok/sRuns great
Q3_K_M342.7 GB25–38 tok/sTight / slow
Q4_K_M465.8 GB19–29 tok/sWon't fit
Q5_K_M560.8 GB17–25 tok/sWon't fit
Q6_K625.9 GB15–22 tok/sWon't fit
Q8_0801.4 GB12–18 tok/sWon't fit
FP161508.0 GB7–10 tok/sWon't fit

Ran GLM-5.2 (MoE) on a Mac Studio M3 Ultra (512GB)? Add your real numbers →