Ollama, Pinokio (various tools), and Whisper are my most used.

Intend to have Florence 2 and possibly another image tagging model, *maybe* a video captioning model but those use a ton of resources, but I hope to integrate them into a “macro” I’m building to do a ton of media organization and captioning stuff. Little experiments have been really good but I’ve not had the time to work out the details and formalize it.