// RUN — FITS

Can the Apple M2 Max 96GB run CLIP (ResNet-50)?

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

CLIP (ResNet-50) on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1293k 1535-1851 t/s ~38.4-46.3 (slow)
Q8 yes 1294k 3070-3702 t/s ~76.7-92.6 (slow)
Q4 yes 1295k 5482.1-6610.8 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.

→ All models on the Apple M2 Max 96GB → CLIP (ResNet-50) specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run CLIP (ResNet-50)?▶

Yes. At Q4 it generates ~5482.1-6610.8 tok/s and fits up to 1295k context; beyond that it spills to SSD swap and slows to ~137.1-165.3 tok/s.

How much context fits?▶

At Q4, up to about 1295k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.