// RUN โ€” FITS

Can the Apple M2 Ultra 192GB run RMBG v2.0?

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

RMBG v2.0 on the Apple M2 Ultra 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2607k 1230.8-1484.2 t/s ~15.4-18.6 (slow)
Q8 yes 2610k 2461.5-2968.3 t/s ~30.8-37.1 (slow)
Q4 yes 2612k 4395.6-5300.6 t/s ~54.9-66.3 (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 M2 Ultra 192GB run RMBG v2.0?โ–ถ

Yes. At Q4 it generates ~4395.6-5300.6 tok/s and fits up to 2612k context; beyond that it spills to SSD swap and slows to ~54.9-66.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2612k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.