// RUN — FITS

Can the Jetson Thor T3000 run Orion Star (猎户星空大模型)?

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

Orion Star (猎户星空大模型) on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 no
Q8 yes 81k 14.2-17 t/s ~0.5-0.6 (slow)
Q4 yes 119k 25.4-30.3 t/s ~0.9-1.1 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the Jetson Thor T3000 run Orion Star (猎户星空大模型)?

Yes. At Q4 it generates ~25.4-30.3 tok/s and fits up to 119k context; beyond that it spills to SSD swap and slows to ~0.9-1.1 tok/s.

How much context fits?

At Q4, up to about 119k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.