// RUN โ€” FITS

Can the NVIDIA Jetson T3000 run YaYi 2.0?

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

YaYi 2.0 on the NVIDIA Jetson T3000

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 no โ€” โ€” โ€”
Q4 yes 40k 11.9-14.1 t/s ~0.4-0.5 (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 T3000 run YaYi 2.0?โ–ถ

Yes. At Q4 it generates ~11.9-14.1 tok/s and fits up to 40k context; beyond that it spills to SSD swap and slows to ~0.4-0.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 40k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.