// RUN — FITS

Can the GMKtec EVO-X3 run Very Deep VAEs (ImageNet-64)?

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

Very Deep VAEs (ImageNet-64) on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1731k 665.6-809 t/s ~26-31.6 (slow)
Q8 yes 1733k 1331.2-1617.9 t/s ~52-63.2 (slow)
Q4 yes 1734k 2377.1-2889.1 t/s ~92.9-112.9 (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 → Very Deep VAEs (ImageNet-64) specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Very Deep VAEs (ImageNet-64)?▶

Yes. At Q4 it generates ~2377.1-2889.1 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~92.9-112.9 tok/s.

How much context fits?▶

At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.