I really want to try this out but keep getting errors for each HF model I try

I want to try on a free hosted HF model to test. I cannot run a local model on this notebook computer. The problem I THINK is I don't know how to access a currently free model on HF, and/ or its not using OpenAI style chat completion end points. I don't know, I just want to try making some low-poly Blender models. I need baby steps cause nothing is working. Every step in README was followed, got the CPU version, installed, selected HF provider, tried a LOT of HF models, even got access granted for Llama-3.3-70B-Instruct, proper API keys, fine grain inference permission access token, every time is 404 error for chat completions.