// RUN โ€” FITS

Can the Jetson Thor T3000 run Pleias 1.0 1.2B?

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

Pleias 1.0 1.2B on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 380k 83-99 t/s ~3-3.6 (slow)
Q8 yes 398k 166.1-197.9 t/s ~6.1-7.3 (slow)
Q4 yes 406k 296.6-353.4 t/s ~10.9-12.9 (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 Pleias 1.0 1.2B?โ–ถ

Yes. At Q4 it generates ~296.6-353.4 tok/s and fits up to 406k context; beyond that it spills to SSD swap and slows to ~10.9-12.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 406k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.