// RUN — FITS

Can the GMKtec EVO-X3 run T5-3B?

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

T5-3B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1649k 29.7-36.1 t/s ~1.2-1.4 (slow)
Q8 yes 1692k 59.4-72.2 t/s ~2.3-2.8 (slow)
Q4 yes 1711k 106.1-129 t/s ~4.1-5 (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 → T5-3B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run T5-3B?▶

Yes. At Q4 it generates ~106.1-129 tok/s and fits up to 1711k context; beyond that it spills to SSD swap and slows to ~4.1-5 tok/s.

How much context fits?▶

At Q4, up to about 1711k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.