can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Max (128GB) run North Mini Code 1.0 (MoE)?

North · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: North Mini Code 1.0 (MoE) at FP16 · 61.0 GB · 43–65 tok/s on a MacBook Pro M4 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB103–154 tok/sRuns great
Q3_K_M14.2 GB93–140 tok/sRuns great
Q4_K_M19.2 GB83–124 tok/sRuns great
Q5_K_M23.0 GB77–115 tok/sRuns great
Q6_K25.5 GB73–109 tok/sRuns great
Q8_032.4 GB64–96 tok/sRuns great
FP1661.0 GB43–65 tok/sRuns great

Ran North Mini Code 1.0 (MoE) on a MacBook Pro M4 Max (128GB)? Add your real numbers →