NVIDIA AI Podcast cover image

MosaicML's Naveen Rao on Making Custom LLMs More Accessible - Ep. 199

NVIDIA AI Podcast

00:00

Mosaic ML's Roadmap for the Future

We found 30 to 50% cheaper performance per dollar. Even performance normalized, and to cost normalized rather, we saw a pretty big gain here. And that's fantastic cost saving. So all of it coming together is really driving the price down to a point where it's going to be just much more accessible by the community. Right. That is the story for us. Like we love it because it's like that's what we want to do. Everybody could do this. Wild.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app