// RUN — FITS

Can the GMKtec EVO-X3 run Yi-1.5-9B?

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

Yi-1.5-9B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 733k 9.4-11.5 t/s ~0.4-0.4 (slow)
Q8 yes 800k 18.8-22.9 t/s ~0.7-0.9 (slow)
Q4 yes 830k 33.7-40.9 t/s ~1.3-1.6 (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 → Yi-1.5-9B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Yi-1.5-9B?▶

Yes. At Q4 it generates ~33.7-40.9 tok/s and fits up to 830k context; beyond that it spills to SSD swap and slows to ~1.3-1.6 tok/s.

How much context fits?▶

At Q4, up to about 830k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.