// RUN โ€” FITS

Can the GMKtec EVO-X3 run Reason-ModernColBERT?

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

Reason-ModernColBERT on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1730k 554.7-674.1 t/s ~21.7-26.3 (slow)
Q8 yes 1733k 1109.3-1348.3 t/s ~43.3-52.7 (slow)
Q4 yes 1734k 1981-2407.6 t/s ~77.4-94 (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 Reason-ModernColBERT?โ–ถ

Yes. At Q4 it generates ~1981-2407.6 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~77.4-94 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.