// RUN — FITS

Can the GMKtec EVO-X3 run phi-3.5-mini?

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

phi-3.5-mini on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1619k 21.9-26.6 t/s ~0.9-1 (slow)
Q8 yes 1677k 43.8-53.2 t/s ~1.7-2.1 (slow)
Q4 yes 1702k 78.2-95 t/s ~3.1-3.7 (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 → phi-3.5-mini specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run phi-3.5-mini?▶

Yes. At Q4 it generates ~78.2-95 tok/s and fits up to 1702k context; beyond that it spills to SSD swap and slows to ~3.1-3.7 tok/s.

How much context fits?▶

At Q4, up to about 1702k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.