// RUN — FITS

Can the GMKtec EVO-X3 run Gemma 7B?

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

Gemma 7B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 737k 9.7-11.8 t/s ~0.4-0.5 (slow)
Q8 yes 802k 19.5-23.7 t/s ~0.8-0.9 (slow)
Q4 yes 831k 34.8-42.3 t/s ~1.4-1.7 (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 → Gemma 7B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Gemma 7B?▶

Yes. At Q4 it generates ~34.8-42.3 tok/s and fits up to 831k context; beyond that it spills to SSD swap and slows to ~1.4-1.7 tok/s.

How much context fits?▶

At Q4, up to about 831k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.