can-i-run-this-llm

Can I run this LLM?

Can a Mac mini M6 (24GB) run GLM-4.7 Flash (MoE)?

GLM · MIT · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4.7 Flash (MoE) at Q2_K · 11.3 GB · 57–85 tok/s on a Mac mini M6 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.3 GB57–85 tok/sRuns great
Q3_K_M14.6 GB49–73 tok/sTight / slow
Q4_K_M18.3 GB42–63 tok/sWon't fit
Q5_K_M21.4 GB38–57 tok/sWon't fit
Q6_K24.7 GB34–51 tok/sWon't fit
Q8_031.8 GB28–42 tok/sWon't fit
FP1659.9 GB17–25 tok/sWon't fit

Ran GLM-4.7 Flash (MoE) on a Mac mini M6 (24GB)? Add your real numbers →