// RUN — FITS

Can the Apple M3 Max 36GB run base LM+GNN+kNN?

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

base LM+GNN+kNN on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 463k 372.3-448.9 t/s ~12.4-15 (slow)
Q8 yes 467k 744.5-897.8 t/s ~24.8-29.9 (slow)
Q4 yes 469k 1329.5-1603.2 t/s ~44.3-53.4 (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 → base LM+GNN+kNN specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run base LM+GNN+kNN?▶

Yes. At Q4 it generates ~1329.5-1603.2 tok/s and fits up to 469k context; beyond that it spills to SSD swap and slows to ~44.3-53.4 tok/s.

How much context fits?▶

At Q4, up to about 469k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.