// RUN — FITS

Can the NVIDIA Jetson T2000 run ERNIE-4.5-0.3B?

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

ERNIE-4.5-0.3B on the NVIDIA Jetson T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 186k 138.9-165.5 t/s ~10.1-12.1 (slow)
Q8 yes 191k 277.8-331.1 t/s ~20.3-24.2 (slow)
Q4 yes 194k 496.1-591.2 t/s ~36.2-43.2 (slow)

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

→ All models on the NVIDIA Jetson T2000 → ERNIE-4.5-0.3B specs → Other hardware

FAQ

Can the NVIDIA Jetson T2000 run ERNIE-4.5-0.3B?▶

Yes. At Q4 it generates ~496.1-591.2 tok/s and fits up to 194k context; beyond that it spills to SSD swap and slows to ~36.2-43.2 tok/s.

How much context fits?▶

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