// RUN โ€” FITS

Can the NVIDIA Jetson T2000 run CodeT5+?

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

CodeT5+ on the NVIDIA Jetson T2000

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 no โ€” โ€” โ€”
Q4 yes 15k 11.2-13.3 t/s ~0.8-1 (slow)

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

FAQ

Can the NVIDIA Jetson T2000 run CodeT5+?โ–ถ

Yes. At Q4 it generates ~11.2-13.3 tok/s and fits up to 15k context; beyond that it spills to SSD swap and slows to ~0.8-1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 15k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.