// RUN โ€” FITS

Can the NVIDIA RTX 6000 Ada 48GB run Granite Vision 3.2 2B?

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

Granite Vision 3.2 2B on the NVIDIA RTX 6000 Ada 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 560k 117.6-140.1 t/s ~4.9-5.8 (slow)
Q8 yes 605k 235.2-280.3 t/s ~9.8-11.7 (slow)
Q4 yes 625k 419.9-500.5 t/s ~17.5-20.9 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the NVIDIA RTX 6000 Ada 48GB run Granite Vision 3.2 2B?โ–ถ

Yes. At Q4 it generates ~419.9-500.5 tok/s and fits up to 625k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~17.5-20.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 625k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.