// RUN — FITS

Can the GMKtec EVO-X3 run Retrieval-Augmented Generator?

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

Retrieval-Augmented Generator on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1716k 132.9-161.5 t/s ~5.2-6.3 (slow)
Q8 yes 1725k 265.8-323.1 t/s ~10.4-12.6 (slow)
Q4 yes 1730k 474.7-576.9 t/s ~18.5-22.5 (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 → Retrieval-Augmented Generator specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Retrieval-Augmented Generator?▶

Yes. At Q4 it generates ~474.7-576.9 tok/s and fits up to 1730k context; beyond that it spills to SSD swap and slows to ~18.5-22.5 tok/s.

How much context fits?▶

At Q4, up to about 1730k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.