I run ollama and auto1111 on my desktop when it’s powers on. Using open-webui in my homelab always on, and also connected to openrouter. This way I can always use openwebui with openrouter models and it’s pretty cheap per query and a little more private that using a big tech chatbot. And if I want local, I turn on the desktop and have local lamma and stab diff.

I also get bugger all benefit out of it., it’s a cute toy.

Haven’t had any rate limiting issues on my private instance. I really thought it’d stop working honestly.

Not sure why you’d be quickly rate limited as a single user, from the GH issues I read they expected we’d have no issues keeping under API limits

Only for niche topics, and using a self-hosted private front end (redlib) I deleted my account at the API death, so it’s only for researching things usually.

God I miss this time on the web