// RUN โ€” FITS

Can the NVIDIA Jetson T2000 run Pleias 1.0 350m?

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

Pleias 1.0 350m on the NVIDIA Jetson T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 186k 142.9-170.3 t/s ~10.4-12.4 (slow)
Q8 yes 191k 285.7-340.5 t/s ~20.9-24.9 (slow)
Q4 yes 194k 510.3-608.1 t/s ~37.2-44.4 (slow)

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

FAQ

Can the NVIDIA Jetson T2000 run Pleias 1.0 350m?โ–ถ

Yes. At Q4 it generates ~510.3-608.1 tok/s and fits up to 194k context; beyond that it spills to SSD swap and slows to ~37.2-44.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 194k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.