// RUN โ€” FITS

Can the Apple M3 Max 128GB run XLNet?

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

XLNet on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1725k 400-482.4 t/s ~10-12.1 (slow)
Q8 yes 1730k 800-964.7 t/s ~20-24.1 (slow)
Q4 yes 1732k 1428.6-1722.7 t/s ~35.7-43.1 (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 M3 Max 128GB run XLNet?โ–ถ

Yes. At Q4 it generates ~1428.6-1722.7 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~35.7-43.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1732k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.