Jev · AI Beat

29 Sep 2026 · AI Beat Desk

Home-Trained and Jev-Accurate

Jeff is a set of Jev-compatible decision models — Qwen3.5 and Gemma 4 fine-tunes — trained from scratch by a single developer in 2–3.5 hours on one RTX PRO 6000. The 2B variant hits 83.1% on five public benchmarks where Jev scores 83.0%, closing the quality gap that made every prior open replica a workaround rather than a replacement.

26 Sep 2026 · AI Beat Desk

Jev on Your Own Metal

Ollaya ships as a Rust daemon that pulls open decision models (Laya, Decider, NLI, GLiClass, Von, Qwen3guard) locally and serves them behind a TypeSafe-compatible API. Set an environment variable and existing Jev clients point at localhost — 8–10 ms per five-question request on a 4090, no API key, Apache-2.0.