GoKawiilKev: Open-source small decision models built on Qwen3.5 released with training code
A developer has released Kev, a family of small decision-making models (0.8B, 4B, and 9B parameters) built on Qwen3.5, inspired by the architecture behind Jev. The models handle yes/no, multiple-choice, and rating questions within a single request and are compatible with TypeSafe's System One API, meaning developers can run Kev locally instead of relying on that hosted service. Full training code, evaluation data, and a web playground are included, and the models run on both CUDA and Apple Silicon hardware.
GoKawiil's interpretation of the reporting above, not reported fact.
By offering a self-hostable, open alternative to a proprietary decision-model API, Kev lowers the barrier for developers who want structured classification and scoring capabilities—like ticket triage or sentiment scoring—without depending on external services or paying per-call fees. Its drop-in API compatibility with System One also signals a broader trend of open models targeting niche, task-specific commercial offerings rather than general chat use cases.
- Kev offers 0.8B, 4B, and 9B parameter models built on Qwen3.5 for structured decision tasks.
- It supports yes/no, multiple-choice, and rating questions in one request and runs on CUDA or Apple Silicon.
- Its API mirrors TypeSafe's System One, letting developers self-host instead of using the hosted service.
Apple Mac Studio (M2 Max) — Since Kev's 4B and 9B models run natively on Apple Silicon and fit comfortably in 32GB using bf16, a Mac Studio is a great local box for experimenting with these decision models without needing a discrete GPU. It's a solid choice for developers who want to train, serve, and tinker with small LLMs like Kev entirely on-device.
See Apple Mac Studio (M2 Max) on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: github.com, 2026-09-21
Published there as: “Kev: Tiny Jev-like family of decision models built on top of Qwen3.5”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.