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.

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