So if models r released for free / open weights. This should be achievable, is that correct?

Is it simply: someone need to implement it?

What is logistics involved if models r just available on torrents, instead of central repo. Maybe validity of model is not possible?

For music use Finamp or Symfonium. I’ve my music in directories and Finamp is fine.

I’ve been testing coding capabilities a bit (mostly scripts - so that work done by ai is reproducible).

1. Context size is very much a required thing along with model capabilities.
2. Local model can generate good enough script in one shot - but reiterations r crazy
3. Use git to keep files tracked (easy to revert) and make a modular script - main script calls function a, function b etc where functions are relatively self contained (no need to look at others) when u need new capability add function c
4. If something need changing- try to do it urself (unless it’s whole architectural change, then just start new project)

As for image gen + chat . as long as chat model + context + image model fits, u should be fine.

Bought b70 with egpu enclosure and usb4 connection wasn’t really planning to actually run anything but now ended up with llama.cpp with openwebui - kids/parents want to/have to use chat, might as well provide local solution than them using industry options. Also started with ollama and Gemma 4 26b a4b - asked it to write script to setup llama.cpp in container.

Yup. I got so wrapped up in “I need to provide this solution” I forgot to think about terminology.

headscale + tailscale. U will need a very small vps for headscale though.