Kev: Tiny Jev-like family of decision models built on top of Qwen3.5
Kev is a new family of small, open-source decision models built on the Qwen3.5 architecture designed for local deployment. These models allow users to perform tasks like classification, scoring, and urgency detection on their own hardware.
Why it matters
The release of efficient, locally-run decision models lowers the barrier for developers to integrate AI-driven logic into their applications without relying on cloud-based APIs.
Small Jev-like decision models you can train and run yourself.
Kev is a family of small decision models built on Qwen3.5 and based on the architecture described in Jev's Architecture Unmasked . You can use the pretrained weights or train your own. The API matches TypeSafe's System One , so you can point their Python SDK at your local server.
0.8B, 4B, and 9B models, with training code and evaluation data. Yes/no ( noul ), multiple-choice ( choice ), and rating ( score ) questions in the same request. Questions share the input text but can't read each other. Runs on CUDA and Apple Silicon. The 4B and 9B models fit a 32 GB Mac using bf16; see Serving Performance for what to expect on a Mac. A web playground for trying your own inputs and checking how option order affects the answers.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in