Comment on AI Is Starting to Look Like the Dot Com Bubble
jeanma@lemmy.ninja 1 year ago
Of course. Sure, AI image generated stuff are impressive but no way those companies could cover the operational, R&D cost if VC were not injecting shit load of fake money.]
pexavc@lemmy.world 1 year ago
Yeah early this year, I was crunching the numbers on even a simple client to interface with LLM APIs. It never made sense, the monthly cost I would have to charge vs others using it to at least feel financially safe, never felt like a viable business model or real value add. That’s not even including Generative Art, which would definitely be much more. So, don’t even know how any of these companies charging <$10/mo are profitable.
ramblinguy@sh.itjust.works 1 year ago
Generative 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