can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M2 Ultra (192GB) run North Mini Code 1.0 (MoE)?

North · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: North Mini Code 1.0 (MoE) at FP16 · 61.0 GB · 56–85 tok/s on a Mac Studio M2 Ultra (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB118–177 tok/sRuns great
Q3_K_M14.2 GB109–163 tok/sRuns great
Q4_K_M19.2 GB99–149 tok/sRuns great
Q5_K_M23.0 GB93–139 tok/sRuns great
Q6_K25.5 GB89–133 tok/sRuns great
Q8_032.4 GB80–120 tok/sRuns great
FP1661.0 GB56–85 tok/sRuns great

Ran North Mini Code 1.0 (MoE) on a Mac Studio M2 Ultra (192GB)? Add your real numbers →