Clef models arrive in Ollama

Ollama now supports Clef and Clef Flash, Cloudflare's new open-source decision models. They are available through the /v1/systemone endpoint. Clef is 27B and Clef Flash is 9B.

Multimodal decision making

Both models are multimodal: requests can now include images alongside the text state. The image is shared by all questions and scored jointly with them. In an example, the model answered whether a screenshot contained Ollama with a probability of 0.958.

Other changes

  • Models using web search can now perform up to ten searches per response, up from three.
  • Modelfiles now support CAPABILITY declarations, letting model creators explicitly declare what a model can do. Declarations are preserved when creating from GGUF or safetensors, through model inheritance, and on Modelfile export.
  • ollama show and the model list now report only "decision" as the capability for decision models, so clients no longer offer them for general chat, tools, or thinking.
  • Updated llama.cpp and the MLX engine.