Actually not 100% true, you can offload a portion of the model into ram to save VRAM to save money on a crazy gpu and still run a decent model, it just takes a bit longer. I personally can wait a minute for a detailed answer instead of needing it in 5 seconds but of course YMMV

Except it's not. Search engines are censored and cut up by SEO. I know, I've tried.

I also don't want to have to sift through all of the scams when I can ask a community for their input.

I'm blocking you now.

Any question you ask on Lemmy can be answered on Google, so what? That's not why people ask.

People ask because they want to interact with another human about their question. They want to discuss it, ask follow up questions, get multiple points of view, discover a wider field than they expected, etc. If you're just fishing around on Google, you may not even know the proper questions to ask, while opening up the discussion offers the potential to learn stuff from experts you never would have found on your own.

I wouldn't say it's easy to get started...

You have to know about open source AI models, then you have to know what fine tuning is, then you have to know where to go to get software that runs the models, and then finally you need to know what models are compatible with both AMD and Nvidia graphics cards.

Good thought, switch to the NaziBot for real truth /s

wtf?

Like what an awesome hunk musk is, or how great apartheid was for south africa