can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M1 (8GB) run GLM-4 9B?

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

Yes, but it's tight.

Best fit: GLM-4 9B at Q2_K · 4.0 GB · 10–15 tok/s on a MacBook Air M1 (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.0 GB10–15 tok/sTight / slow
Q3_K_M5.0 GB8–13 tok/sWon't fit
Q4_K_M6.2 GB7–10 tok/sWon't fit
Q5_K_M7.1 GB6–9 tok/sWon't fit
Q6_K8.3 GB5–8 tok/sWon't fit
Q8_010.0 GB4–7 tok/sWon't fit
FP1618.8 GB2–4 tok/sWon't fit

Ran GLM-4 9B on a MacBook Air M1 (8GB)? Add your real numbers →