Comment on AI Is Starting to Look Like the Dot Com Bubble
ramblinguy@sh.itjust.works 1 year agoGenerative art is actually much easier to run than LLMs. You can get really high resolutions on SDXL (1024x1024) using only 8gb of Vram (although it’d be slow). There’s no way you can get anything but the smallest of text generative models into that same amount of VRAM.
pexavc@lemmy.world 1 year ago
Oh wow, that’s good to know. I always attributed visual graphics to be way more intensive. Wouldn’t think a text generative model to take up that much Vram
ramblinguy@sh.itjust.works 1 year ago
Sorry, just seeing this now- I think with 24gb of vram, the most you can get is a 4bit quantized 30b model, and even then, I think you’d have to limit it to 2-3k of context. Here’s a chart for size comparisons: postimg.cc/4mxcM3kX
By comparison, with 24gb of vram, I only use half of that to create a batch of 8 768x576 photos. I also sub to mage.space, and I’m pretty sure they’re able to handle all of their volume on an A100 and A10G