Because even very small models will take up a large chunk of your cards VRAM, if not all of it. And then you still have to render the game on top of it.
MangoPenguin@lemmy.blahaj.zone 4 weeks ago
Given that people playing this have GPUs, why not run the AI model locally? I can’t imagine it needs to be a very large model.
EncryptKeeper@lemmy.world 4 weeks ago
MangoPenguin@lemmy.blahaj.zone 4 weeks ago
It looks like a very simple game graphically, so having say 2GB VRAM left over for a small model would probably be viable?
EncryptKeeper@lemmy.world 4 weeks ago
I can’t say for certain but based on how the game is described, I don’t think it’s likely a 2GB model would be viable at all.
MangoPenguin@lemmy.blahaj.zone 4 weeks ago
Probably not a viable game in that case, unless the dev makes people link their own API keys.
humanspiral@lemmy.ca 4 weeks ago
There are 1-2gb vram models that should fit in anything. Game doesn’t appear to be texture heavy, and targetting a 6gb gpu, would cover anything less than 10-12 years old.
EncryptKeeper@lemmy.world 4 weeks ago
A 1-2 min vram model would probably not be sufficient for what the game is trying to do. Those micro models aren’t really for anything beyond basic object image recognition or RAG searching
aksdb@lemmy.world 4 weeks ago
Actually sounds like the perfect use case for a model like Jev. I think Jevos should be able to handle that locally.