Alex Cheema - e/acc (@alexocheema) 's Twitter Profile
Alex Cheema - e/acc

@alexocheema

Building @exolabs | prev @UniOfOxford We're hiring: exolabs.net

ID: 915614943797551104

linkhttps://github.com/exo-explore/exo calendar_today04-10-2017 16:29:48

4,4K Tweet

36,36K Takipçi

2,2K Takip Edilen

Alex Cheema - e/acc (@alexocheema) 's Twitter Profile Photo
Alex Cheema - e/acc
@alexocheema

7 months ago

While Apple has been positioning M4 chips for local AI inference with their unified memory architecture, NVIDIA just undercut them massively. Stacking Project Digits personal computers is now the most affordable way to run frontier LLMs locally. The 1 petaflop headline feels

While Apple has been positioning M4 chips for local AI inference with their unified memory architecture, NVIDIA just undercut them massively. Stacking Project Digits personal computers is now the most affordable way to run frontier LLMs locally. The 1 petaflop headline feels