// RUN — FITS

Can the GMKtec EVO-X3 run Phi-4-Multimodal?

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

Phi-4-Multimodal on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 782k 14.9-18.1 t/s ~0.6-0.7 (slow)
Q8 yes 825k 29.7-36.1 t/s ~1.2-1.4 (slow)
Q4 yes 844k 53.1-64.5 t/s ~2.1-2.5 (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 → Phi-4-Multimodal specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Phi-4-Multimodal?▶

Yes. At Q4 it generates ~53.1-64.5 tok/s and fits up to 844k context; beyond that it spills to SSD swap and slows to ~2.1-2.5 tok/s.

How much context fits?▶

At Q4, up to about 844k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.