// RUN — FITS

Can the GMKtec EVO-X3 run Qwen2.5-14B?

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

Qwen2.5-14B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 515k 5.7-6.9 t/s ~0.2-0.3 (slow)
Q8 yes 604k 11.3-13.8 t/s ~0.4-0.5 (slow)
Q4 yes 644k 20.2-24.6 t/s ~0.8-1 (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 → Qwen2.5-14B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Qwen2.5-14B?▶

Yes. At Q4 it generates ~20.2-24.6 tok/s and fits up to 644k context; beyond that it spills to SSD swap and slows to ~0.8-1 tok/s.

How much context fits?▶

At Q4, up to about 644k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.