// RUN — FITS

Can the GMKtec EVO-X3 run Minerva 7B?

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

Minerva 7B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 755k 11.2-13.7 t/s ~0.4-0.5 (slow)
Q8 yes 811k 22.5-27.3 t/s ~0.9-1.1 (slow)
Q4 yes 836k 40.2-48.8 t/s ~1.6-1.9 (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 → Minerva 7B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Minerva 7B?▶

Yes. At Q4 it generates ~40.2-48.8 tok/s and fits up to 836k context; beyond that it spills to SSD swap and slows to ~1.6-1.9 tok/s.

How much context fits?▶

At Q4, up to about 836k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.