can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M2 (8GB) run GLM-4 9B?

GLM · MIT · estimated for a 8.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GLM-4 9B at Q2_K · 4.0 GB · 15–22 tok/s on a MacBook Air M2 (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB15–22 tok/sRuns great
Q3_K_M5.0 GB12–18 tok/sWon't fit
Q4_K_M6.2 GB10–15 tok/sWon't fit
Q5_K_M7.1 GB9–13 tok/sWon't fit
Q6_K8.3 GB8–11 tok/sWon't fit
Q8_010.0 GB6–10 tok/sWon't fit
FP1618.8 GB3–5 tok/sWon't fit

Ran GLM-4 9B on a MacBook Air M2 (8GB)? Add your real numbers →