// RUN — FITS

Can the GMKtec EVO-X3 run OpenELM-1.1B?

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

OpenELM-1.1B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1702k 77-93.6 t/s ~3-3.7 (slow)
Q8 yes 1718k 154.1-187.3 t/s ~6-7.3 (slow)
Q4 yes 1726k 275.1-334.4 t/s ~10.7-13.1 (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 → OpenELM-1.1B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run OpenELM-1.1B?▶

Yes. At Q4 it generates ~275.1-334.4 tok/s and fits up to 1726k context; beyond that it spills to SSD swap and slows to ~10.7-13.1 tok/s.

How much context fits?▶

At Q4, up to about 1726k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.