// RUN โ€” FITS

Can the GMKtec EVO-X3 run SANA 1.5 4.8B?

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

SANA 1.5 4.8B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1588k 17.3-21.1 t/s ~0.7-0.8 (slow)
Q8 yes 1662k 34.7-42.1 t/s ~1.4-1.6 (slow)
Q4 yes 1694k 61.9-75.2 t/s ~2.4-2.9 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the GMKtec EVO-X3 run SANA 1.5 4.8B?โ–ถ

Yes. At Q4 it generates ~61.9-75.2 tok/s and fits up to 1694k context; beyond that it spills to SSD swap and slows to ~2.4-2.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1694k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.