Clef stops writing answers word by word: one pass scores every question and returns a probability
Cloudflare's 27B multimodal decision model Clef is now available on Ollama, running locally or in Ollama's cloud. It takes a state plus a schema of typed questions and, in one pass over text, JSON or images, scores every answer to every question at once instead of generating a response word by word. On Cloudflare's published Jev Decision Index evaluations Clef beats Jev on most benchmarks, but trails it on When2Call and BRIGHT.