// RUN — FITS

Can the AMD Ryzen AI Max+ 395 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 AMD Ryzen AI Max+ 395

QuantFits?Max contextSpeedBeyond context
FP16 yes 1729k 435.9-532.8 t/s ~17-20.8 (slow)
Q8 yes 1732k 871.8-1065.5 t/s ~34.1-41.6 (slow)
Q4 yes 1733k 1556.8-1902.7 t/s ~60.8-74.3 (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 AMD Ryzen AI Max+ 395 → (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) specs → Other hardware

FAQ

Can the AMD Ryzen AI Max+ 395 run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?▶

Yes. At Q4 it generates ~1556.8-1902.7 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~60.8-74.3 tok/s.

How much context fits?▶

At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.