// RUN โ€” FITS

Can the Apple M4 Max 128GB run Oryx 34B?

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

Oryx 34B on the Apple M4 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 174k 5.5-6.6 t/s ~0.1-0.1 (slow)
Q8 yes 304k 10.9-13.2 t/s ~0.2-0.2 (slow)
Q4 yes 361k 19.5-23.5 t/s ~0.4-0.4 (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 M4 Max 128GB run Oryx 34B?โ–ถ

Yes. At Q4 it generates ~19.5-23.5 tok/s and fits up to 361k context; beyond that it spills to SSD swap and slows to ~0.4-0.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 361k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.