// RUN — FITS

Can the Apple M3 Max 36GB run BERT-RBP?

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

BERT-RBP on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 468k 927.3-1118.2 t/s ~30.9-37.3 (slow)
Q8 yes 470k 1854.5-2236.4 t/s ~61.8-74.5 (slow)
Q4 yes 471k 3311.7-3993.5 t/s ~110.4-133.1 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

→ All models on the Apple M3 Max 36GB → BERT-RBP specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run BERT-RBP?▶

Yes. At Q4 it generates ~3311.7-3993.5 tok/s and fits up to 471k context; beyond that it spills to SSD swap and slows to ~110.4-133.1 tok/s.

How much context fits?▶

At Q4, up to about 471k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.