// RUN โ€” FITS

Can the Apple M4 Max 36GB run ImageBind?

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

ImageBind on the Apple M4 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 443k 199.2-240.2 t/s ~3.6-4.4 (slow)
Q8 yes 457k 398.4-480.4 t/s ~7.3-8.8 (slow)
Q4 yes 464k 711.4-857.8 t/s ~13-15.7 (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 36GB run ImageBind?โ–ถ

Yes. At Q4 it generates ~711.4-857.8 tok/s and fits up to 464k context; beyond that it spills to SSD swap and slows to ~13-15.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 464k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.