// RUN โ€” FITS

Can the GMKtec EVO-X3 run LUKE?

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

LUKE on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1720k 172.3-209.4 t/s ~6.7-8.2 (slow)
Q8 yes 1728k 344.5-418.7 t/s ~13.5-16.4 (slow)
Q4 yes 1731k 615.2-747.7 t/s ~24-29.2 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the GMKtec EVO-X3 run LUKE?โ–ถ

Yes. At Q4 it generates ~615.2-747.7 tok/s and fits up to 1731k context; beyond that it spills to SSD swap and slows to ~24-29.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1731k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.