// RUN โ€” FITS

Can the Apple M2 Max 96GB run TRIMELMext (7M)?

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

TRIMELMext (7M) on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1295k 19428.6-23428.6 t/s ~485.7-585.7 (slow)
Q8 yes 1295k 38857.1-46857.1 t/s ~971.4-1171.4 (slow)
Q4 yes 1295k 69387.8-83673.5 t/s ~1734.7-2091.8 (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 TRIMELMext (7M)?โ–ถ

Yes. At Q4 it generates ~69387.8-83673.5 tok/s and fits up to 1295k context; beyond that it spills to SSD swap and slows to ~1734.7-2091.8 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.