// RUN — FITS

Can the GMKtec EVO-X3 run LLaVA-OV-7B?

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

LLaVA-OV-7B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 751k 10.9-13.3 t/s ~0.4-0.5 (slow)
Q8 yes 809k 21.9-26.6 t/s ~0.9-1 (slow)
Q4 yes 835k 39.1-47.5 t/s ~1.5-1.9 (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 → LLaVA-OV-7B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run LLaVA-OV-7B?▶

Yes. At Q4 it generates ~39.1-47.5 tok/s and fits up to 835k context; beyond that it spills to SSD swap and slows to ~1.5-1.9 tok/s.

How much context fits?▶

At Q4, up to about 835k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.