// RUN — FITS

Can the NVIDIA Jetson T2000 run Qwen2.5-Omni 3B?

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

Qwen2.5-Omni 3B on the NVIDIA Jetson T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 105k 16.7-19.9 t/s ~1.2-1.5 (slow)
Q8 yes 151k 33.3-39.7 t/s ~2.4-2.9 (slow)
Q4 yes 171k 59.5-70.9 t/s ~4.3-5.2 (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 → Qwen2.5-Omni 3B specs → Other hardware

FAQ

Can the NVIDIA Jetson T2000 run Qwen2.5-Omni 3B?▶

Yes. At Q4 it generates ~59.5-70.9 tok/s and fits up to 171k context; beyond that it spills to SSD swap and slows to ~4.3-5.2 tok/s.

How much context fits?▶

At Q4, up to about 171k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.