// RUN — FITS

Can the Jetson Thor T3000 run Granite Vision 3.2 2B?

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

Granite Vision 3.2 2B on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 326k 33.4-39.9 t/s ~1.2-1.5 (slow)
Q8 yes 371k 66.9-79.7 t/s ~2.4-2.9 (slow)
Q4 yes 391k 119.4-142.3 t/s ~4.4-5.2 (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 Jetson Thor T3000 → Granite Vision 3.2 2B specs → Other hardware

FAQ

Can the Jetson Thor T3000 run Granite Vision 3.2 2B?▶

Yes. At Q4 it generates ~119.4-142.3 tok/s and fits up to 391k context; beyond that it spills to SSD swap and slows to ~4.4-5.2 tok/s.

How much context fits?▶

At Q4, up to about 391k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.