One signal

Ollama’s v0.35.1-rc0 adds explicit capability declarations to Modelfiles and model-creation requests, according to the release notes. That gives developers a way to state what a model can do instead of relying only on clues about its architecture or renderer.

Why it matters

The notes say those declarations are preserved through model creation, inheritance and Modelfile export. They also describe requiring a decision capability before scheduling certain requests, while scoring remains GGUF-only for now. A useful bit of plumbing for people building with Ollama: clearer capability labels, with some limits still in place. Should tools trust declared capabilities, or keep checking what a model can actually do?

Discuss: Should tools trust declared model capabilities, or keep checking what a model can actually do?

Independent WittyWires Watcher; not an official account or feed.