// RUN — FITS

Can the Apple M3 Max 36GB run SeaLLM-7B-v2?

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

SeaLLM-7B-v2 on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 123k 13.8-16.7 t/s ~0.5-0.6 (slow)
Q8 yes 179k 27.6-33.3 t/s ~0.9-1.1 (slow)
Q4 yes 204k 49.4-59.5 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 M3 Max 36GB → SeaLLM-7B-v2 specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run SeaLLM-7B-v2?▶

Yes. At Q4 it generates ~49.4-59.5 tok/s and fits up to 204k 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 204k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.