Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

at least supporting at the API level would be great, as this would allow input with OpenAI compatible frontends such as open-webui. bonus for supporting in the built in web ui.

Motivation

currently, it is necessary to use another server such as ollama in order to get multi-modal input with models such as gemma3

Possible Implementation

No response