// RUN — FITS

Can the Jetson Thor T3000 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 Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 411k 538.6-641.9 t/s ~19.7-23.5 (slow)
Q8 yes 414k 1077.2-1283.8 t/s ~39.5-47 (slow)
Q4 yes 415k 1923.6-2292.6 t/s ~70.5-84 (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 Jetson Thor T3000 → (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) specs → Other hardware

FAQ

Can the Jetson Thor T3000 run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?▶

Yes. At Q4 it generates ~1923.6-2292.6 tok/s and fits up to 415k context; beyond that it spills to SSD swap and slows to ~70.5-84 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.