What you’re describing is exactly what I’ve experienced in my time testing out this stuff locally, and I had a hard time figuring out what exactly to blame.

I keep hoping that one day some comment is going to paste a link to some kind of idiot-proof guide or piece of software that’s “90% as good as Claude but running local.”

And by 90% I don’t mean that the model is 90% as good or runs 90% as fast, more like all the other stuff you mentioned is set up out of the box.