// RUN — FITS

Can the GMKtec EVO-X3 run KoGPT?

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

KoGPT on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 773k 13.5-16.4 t/s ~0.5-0.6 (slow)
Q8 yes 820k 27-32.8 t/s ~1.1-1.3 (slow)
Q4 yes 841k 48.2-58.6 t/s ~1.9-2.3 (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 → KoGPT specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run KoGPT?▶

Yes. At Q4 it generates ~48.2-58.6 tok/s and fits up to 841k context; beyond that it spills to SSD swap and slows to ~1.9-2.3 tok/s.

How much context fits?▶

At Q4, up to about 841k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.