Well, I'm sure an NVDA addon with this will be here soon. Just amazing how far things have come. I mean, I hope there's a Windows version of the Llava part of this anyway.
llamafile is the new best way to run a LLM on your own computer:
@MutedTrampet Yeah, I ran Ollama, with a few models, and it's like 3 tokens per second lol. But once they start using more than just NVIDIA GPU's, I think it'll get faster for people like me that have AMD GPU's.
@MutedTrampet@devinprater Turns out the descriptions it provides are nowhere as good as GPT4, though, so probably not worth it for screen reader integration yet.
Add comment