// RUN โ€” FITS

Can the Apple M3 Max 48GB run Minerva 3B?

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

Minerva 3B on the Apple M3 Max 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 545k 45.3-54.7 t/s ~1.1-1.4 (slow)
Q8 yes 591k 90.7-109.3 t/s ~2.3-2.7 (slow)
Q4 yes 611k 161.9-195.2 t/s ~4-4.9 (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 48GB run Minerva 3B?โ–ถ

Yes. At Q4 it generates ~161.9-195.2 tok/s and fits up to 611k context; beyond that it spills to SSD swap and slows to ~4-4.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 611k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.