// RUN — FITS

Can the GMKtec EVO-X3 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 GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1644k 27.9-33.9 t/s ~1.1-1.3 (slow)
Q8 yes 1689k 55.8-67.9 t/s ~2.2-2.7 (slow)
Q4 yes 1709k 99.7-121.2 t/s ~3.9-4.7 (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 GMKtec EVO-X3 → Granite Vision 3.2 2B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Granite Vision 3.2 2B?▶

Yes. At Q4 it generates ~99.7-121.2 tok/s and fits up to 1709k context; beyond that it spills to SSD swap and slows to ~3.9-4.7 tok/s.

How much context fits?▶

At Q4, up to about 1709k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.