// RUN โ€” FITS

Can the Apple M4 Max 64GB run CLIP (ResNet-50)?

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

CLIP (ResNet-50) on the Apple M4 Max 64GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 853k 2095.3-2526.6 t/s ~38.4-46.3 (slow)
Q8 yes 855k 4190.5-5053.3 t/s ~76.7-92.6 (slow)
Q4 yes 855k 7483.1-9023.7 t/s ~137.1-165.3 (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 64GB run CLIP (ResNet-50)?โ–ถ

Yes. At Q4 it generates ~7483.1-9023.7 tok/s and fits up to 855k context; beyond that it spills to SSD swap and slows to ~137.1-165.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 855k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.