// RUN โ€” FITS

Can the Apple M3 Max 36GB run North Mini Code 1.0?

Yes โ€” here's how fast and up to what context, with real measured numbers.

North Mini Code 1.0 on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 3k 6.8-8.2 t/s ~0.2-0.3 (slow)
Q4 yes 54k 12.1-14.6 t/s ~0.4-0.5 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the Apple M3 Max 36GB run North Mini Code 1.0?โ–ถ

Yes. At Q4 it generates ~12.1-14.6 tok/s and fits up to 54k context; beyond that it spills to SSD swap and slows to ~0.4-0.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 54k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.