// RUN โ€” FITS

Can the GMKtec EVO-X3 run Viking?

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

Viking on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 182k 2.5-3.1 t/s ~0.1-0.1 (slow)
Q8 yes 308k 5-6.1 t/s ~0.2-0.2 (slow)
Q4 yes 363k 9-10.9 t/s ~0.4-0.4 (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 Viking?โ–ถ

Yes. At Q4 it generates ~9-10.9 tok/s and fits up to 363k context; beyond that it spills to SSD swap and slows to ~0.4-0.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 363k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.