// RUN — FITS

Can the GMKtec EVO-X3 run Stable Diffusion 3.5 Large?

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

Stable Diffusion 3.5 Large on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 744k 10.3-12.5 t/s ~0.4-0.5 (slow)
Q8 yes 806k 20.5-25 t/s ~0.8-1 (slow)
Q4 yes 833k 36.7-44.6 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 → Stable Diffusion 3.5 Large specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Stable Diffusion 3.5 Large?▶

Yes. At Q4 it generates ~36.7-44.6 tok/s and fits up to 833k 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 833k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.