// RUN — FITS

Can the Apple M2 Max 96GB run SEA-LION-v1-7B-IT?

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

SEA-LION-v1-7B-IT on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 533k 18.1-21.9 t/s ~0.5-0.5 (slow)
Q8 yes 591k 36.3-43.7 t/s ~0.9-1.1 (slow)
Q4 yes 616k 64.8-78.1 t/s ~1.6-2 (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 → SEA-LION-v1-7B-IT specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run SEA-LION-v1-7B-IT?▶

Yes. At Q4 it generates ~64.8-78.1 tok/s and fits up to 616k context; beyond that it spills to SSD swap and slows to ~1.6-2 tok/s.

How much context fits?▶

At Q4, up to about 616k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.