// RUN — FITS

Can the Intel Gaudi 3 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 Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1768k 5800-7200 t/s ~62.7-77.8 (slow)
Q8 yes 1771k 11600-14400 t/s ~125.4-155.7 (slow)
Q4 yes 1772k 20714.3-25714.3 t/s ~223.9-278 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the Intel Gaudi 3 run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?

Yes. At Q4 it generates ~20714.3-25714.3 tok/s and fits up to 1772k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~223.9-278 tok/s.

How much context fits?

At Q4, up to about 1772k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.