TheBluePillock

I would love to be corrected, but when I looked into it, it sounded like you’d probably want 32gb VRAM or better for actual chat ability. You have to have enough memory to load the model, and anything not handled by your GPU takes a major performance hit. Then, you probably want to aim for a 72 billion parameter model. That’s a decently conversational level and maybe close to the one you’re using (but it’s possible they’re higher? I’m just guessing). I think 34B models are comparatively more prone to hallucination and inaccuracy. It sounded like the 32GB VRAM was kinda entry point for the 72B models so I stopped looking, because I can’t afford that.

So somebody with more experience or knowledge can hopefully correct me or give a better explanation, but just in case, maybe this is a helpful starting point for someone.

You can download models on huggingface.co and interact with them through a web-ui like this one.

I was in the same boat and stumbled on Dawncaster. It’s the best mobile game I’ve ever played. I’d honestly play it on PC too, but it’s strangely mobile only. You could compare it to Slay the Spire, but I have found Dawncaster much more satisfying and fun for me personally. Also very active devs who are opposed to micro-transactions.