// RUN โ€” FITS

Can the Apple M1 Ultra 128GB run ruGPT-3.5 13B?

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

ruGPT-3.5 13B on the Apple M1 Ultra 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 535k 20.9-25.2 t/s ~0.3-0.3 (slow)
Q8 yes 615k 41.8-50.5 t/s ~0.5-0.6 (slow)
Q4 yes 650k 74.7-90.1 t/s ~0.9-1.1 (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 ruGPT-3.5 13B?โ–ถ

Yes. At Q4 it generates ~74.7-90.1 tok/s and fits up to 650k context; beyond that it spills to SSD swap and slows to ~0.9-1.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 650k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.