// RUN — FITS

Can the GMKtec EVO-X3 run Qwen-VL?

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

Qwen-VL on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 721k 8.7-10.5 t/s ~0.3-0.4 (slow)
Q8 yes 794k 17.3-21.1 t/s ~0.7-0.8 (slow)
Q4 yes 826k 31-37.6 t/s ~1.2-1.5 (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 → Qwen-VL specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Qwen-VL?▶

Yes. At Q4 it generates ~31-37.6 tok/s and fits up to 826k context; beyond that it spills to SSD swap and slows to ~1.2-1.5 tok/s.

How much context fits?▶

At Q4, up to about 826k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.