// RUN โ€” FITS

Can the Apple M1 Ultra 128GB run Generative BST?

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

Generative BST on the Apple M1 Ultra 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 724k 28.8-34.8 t/s ~0.4-0.4 (slow)
Q8 yes 796k 57.7-69.6 t/s ~0.7-0.9 (slow)
Q4 yes 827k 103-124.2 t/s ~1.3-1.6 (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 M1 Ultra 128GB run Generative BST?โ–ถ

Yes. At Q4 it generates ~103-124.2 tok/s and fits up to 827k context; beyond that it spills to SSD swap and slows to ~1.3-1.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 827k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.