can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M3 (8GB) run 1-bit Bonsai 27B?

Bonsai · Apache 2.0 · estimated for a 8.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: 1-bit Bonsai 27B at Q1_0 · 3.8 GB · 11–17 tok/s on a MacBook Air M3 (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q1_03.8 GB11–17 tok/sTight / slow

Ran 1-bit Bonsai 27B on a MacBook Air M3 (8GB)? Add your real numbers →