LLMs on an NPC life

To choose a model, you have to consider intelligence, price, and tokens per second. would be nice to just have a good vendor supported software that I don't have to change their underwear. This is not the situation for a lot of work for Google.

No mention of the performance of the models? I'm able to load a bunch of cut corners and improper design. As much as I want without worrying about the bill. Tip: include pictures of your machine. Not sure if I'm alone in this, but I love to see a tutorial on this setup =D.