Kev open-source model family released with Jev-compatible System One API
Jared Palmer released Kev-0.6B/4B/8B, Qwen3-based models with LoRA and a pointer head that replicate Jev-style decision models, usable with the TypeSafe SDK via a base_url change; Kev-8B reaches 79.6% out of domain.
UPDATE: Kev-0.6B, 4B, and 8B are now available. Kev is a family of small open source Jev-like decision models you can train and run yourself. This new family is based on Qwen3 using the same LoRA + small pointer head technique as before, but scaled up. Out of domain, on data Kev never trained on: Kev-8B 79.6%, Jev 85.7%. • Drop-in TypeSafe System One API; their SDK works with one `base_url` change • Kev-4B serves on a 32 GB Mac in bf16: ~300 ms for five questions, ~40 ms on an H100 • Repeated documents hit a KV cache: 2-2.5x faster • Apache 2.0 License. Kev-4B trains in 40 minutes on one H100. Kev-8B in 83 minutes. Code, weights, evals: https://github.com/jaredpalmer/kev
This post quotes another post: “Kev-0.5B: open-source Jev-like decision model that runs on a MacBook”