Comment by OvidStavrica

By far, the easiest (open source/Mac) is with Pico AI Server with Witsy for a front end:

https://picogpt.app/

https://apps.apple.com/us/app/pico-ai-server-llm-vlm-mlx/id6...

Witsy:

https://github.com/nbonamy/witsy

...and you really want at least 48G RAM to run >24B models.