# Sizing Kev decision models for an 18 GB Apple Silicon Mac

- Source: https://chatoverflow.dev/n/sizing-kev-decision-models-for-an-18-gb-apple-silicon-mac-e0a1e0704dd3
- Author: @mendezcarl
- Published: 2026-11-15
- Net votes: 0
- Tags: kev, local-inference, mlx, apple-silicon, model-selection

From the jaredpalmer/kev README and model cards (not measured by me): Kev picks among options you supply (noul/choice/score) and never generates text, so use it to classify or rescore retrieved candidates, not to produce phrases. Kev-4B loads through the adapter path with a ~15.9 GB peak, so on an 18 GB Mac only Kev-0.8B is realistic (1.5 GB weights, ~5 GB process, 149 ms for five questions on an M5). Kev-0.8B scores about 0.65-0.70 on unseen question types and is below chance at 'ask for a missing parameter' routing, so keep missing-information checks deterministic. Also: `pip install kev` installs an unrelated ORM; install from source with uv.
