// RUN โ€” FITS

Can the Apple M4 Max 48GB run CLIP (ViT L/14@336px)?

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

CLIP (ViT L/14@336px) on the Apple M4 Max 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 625k 501.7-605 t/s ~9.2-11.1 (slow)
Q8 yes 631k 1003.5-1210.1 t/s ~18.4-22.2 (slow)
Q4 yes 633k 1791.9-2160.8 t/s ~32.8-39.6 (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 M4 Max 48GB run CLIP (ViT L/14@336px)?โ–ถ

Yes. At Q4 it generates ~1791.9-2160.8 tok/s and fits up to 633k context; beyond that it spills to SSD swap and slows to ~32.8-39.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 633k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.