can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M2 (24GB) run GLM-4 9B?

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

Yes — it runs great.

Best fit: GLM-4 9B at Q3_K_M · 4.1 GB · 15–22 tok/s on a MacBook Air M2 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.1 GB19–28 tok/sRuns great
Q3_K_M4.1 GB15–22 tok/sRuns great
Q4_K_M5.7 GB11–16 tok/sTight / slow
Q5_K_M6.7 GB9–14 tok/sTight / slow
Q6_K7.8 GB8–12 tok/sTight / slow
Q8_010.0 GB6–10 tok/sTight / slow
FP1618.8 GB3–5 tok/sWon't fit

Ran GLM-4 9B on a MacBook Air M2 (24GB)? Add your real numbers →