// RUN โ€” FITS

Can the GMKtec EVO-X3 run HiFi - NN?

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

HiFi - NN on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1735k 27733.3-33706.7 t/s ~1083.3-1316.7 (slow)
Q8 yes 1735k 55466.7-67413.3 t/s ~2166.7-2633.3 (slow)
Q4 yes 1735k 99047.6-120381 t/s ~3869-4702.4 (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 HiFi - NN?โ–ถ

Yes. At Q4 it generates ~99047.6-120381 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~3869-4702.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.