// RUN — FITS

Can the Jetson Thor T3000 run Retrieval-Augmented Generator?

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

Retrieval-Augmented Generator on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 397k 159.2-189.7 t/s ~5.8-6.9 (slow)
Q8 yes 407k 318.4-379.4 t/s ~11.7-13.9 (slow)
Q4 yes 411k 568.5-677.5 t/s ~20.8-24.8 (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 → Retrieval-Augmented Generator specs → Other hardware

FAQ

Can the Jetson Thor T3000 run Retrieval-Augmented Generator?▶

Yes. At Q4 it generates ~568.5-677.5 tok/s and fits up to 411k context; beyond that it spills to SSD swap and slows to ~20.8-24.8 tok/s.

How much context fits?▶

At Q4, up to about 411k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.