// RUN — FITS

Can the Apple M2 Max 32GB run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?

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

(ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) on the Apple M2 Max 32GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 411k 735.1-886.5 t/s ~18.4-22.2 (slow)
Q8 yes 414k 1470.3-1773 t/s ~36.8-44.3 (slow)
Q4 yes 415k 2625.5-3166 t/s ~65.6-79.2 (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 32GB → (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) specs → Other hardware

FAQ

Can the Apple M2 Max 32GB run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?▶

Yes. At Q4 it generates ~2625.5-3166 tok/s and fits up to 415k context; beyond that it spills to SSD swap and slows to ~65.6-79.2 tok/s.

How much context fits?▶

At Q4, up to about 415k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.