// RUN — FITS

Can the Jetson Thor T3000 run Generative BST?

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

Generative BST on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 64k 10.6-12.6 t/s ~0.4-0.5 (slow)
Q8 yes 136k 21.1-25.2 t/s ~0.8-0.9 (slow)
Q4 yes 168k 37.7-45 t/s ~1.4-1.6 (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 → Generative BST specs → Other hardware

FAQ

Can the Jetson Thor T3000 run Generative BST?▶

Yes. At Q4 it generates ~37.7-45 tok/s and fits up to 168k context; beyond that it spills to SSD swap and slows to ~1.4-1.6 tok/s.

How much context fits?▶

At Q4, up to about 168k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.