// RUN โ€” FITS

Can the Apple M2 Max 96GB run SPIDER2?

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

SPIDER2 on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1295k 332083.1-400453.2 t/s ~8302.1-10011.3 (slow)
Q8 yes 1295k 664166.3-800906.4 t/s ~16604.2-20022.7 (slow)
Q4 yes 1295k 1186011.2-1430190 t/s ~29650.3-35754.7 (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 M2 Max 96GB run SPIDER2?โ–ถ

Yes. At Q4 it generates ~1186011.2-1430190 tok/s and fits up to 1295k context; beyond that it spills to SSD swap and slows to ~29650.3-35754.7 tok/s.

How much context fits?โ–ถ

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