Chatting with multiple models simultaneously

[remon-nashid]

This is certainly just a nice-to-have in such a powerful llm chatting app.

• Not necessarily a MoA or anything fancy, just the ability to send a prompt to multiple models and see the responses side by side.
• Ollama supports parallel execution, so with a couple of small models, this is quite feasible on a half decent GPU.

[ggozad]

It's kind of difficult to see how this could work UI-wise...
I don't think I can prioritize this but if there is interest from someone else building it will be happy to help.

[remon-nashid]

Absolutely. Just keeping the idea out there shall other users find it useful and be able to chime in with ideas. Just for the reference, it looks like this in openwebui: