Isn't there a simpler way to run LLMs / models locally?

You are not the only one to feel this pain.

github.com

GitHub - jimdawdy-hub/Local-LLM-Launcher-GUI: A friendly GUI for running local LLMs with vLLM...

A friendly GUI for running local LLMs with vLLM and llama.cpp — hardware-aware traffic-light guidance for every setting. Built on ideas from vllm-cli (Chen-zexi).

Feel free to contribute!