can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M5 (32GB) run North Mini Code 1.0 (MoE)?

North · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: North Mini Code 1.0 (MoE) at Q3_K_M · 14.2 GB · 43–64 tok/s on a MacBook Air/Pro M5 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB51–76 tok/sRuns great
Q3_K_M14.2 GB43–64 tok/sRuns great
Q4_K_M19.2 GB36–53 tok/sTight / slow
Q5_K_M23.0 GB32–47 tok/sWon't fit
Q6_K25.5 GB29–44 tok/sWon't fit
Q8_032.4 GB25–37 tok/sWon't fit
FP1661.0 GB15–22 tok/sWon't fit

Ran North Mini Code 1.0 (MoE) on a MacBook Air/Pro M5 (32GB)? Add your real numbers →