// RUN — FITS

Can the GMKtec EVO-X3 run ProGen2-xlarge?

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

ProGen2-xlarge on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 770k 13-15.8 t/s ~0.5-0.6 (slow)
Q8 yes 819k 26-31.6 t/s ~1-1.2 (slow)
Q4 yes 840k 46.4-56.4 t/s ~1.8-2.2 (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 GMKtec EVO-X3 → ProGen2-xlarge specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run ProGen2-xlarge?▶

Yes. At Q4 it generates ~46.4-56.4 tok/s and fits up to 840k context; beyond that it spills to SSD swap and slows to ~1.8-2.2 tok/s.

How much context fits?▶

At Q4, up to about 840k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.