Nvidia and Perplexity partner to bring AI to local hardware
Nvidia and Perplexity have partnered to run AI search models directly on local hardware using Nvidia GPUs. By shifting processing from the cloud to individual computers, this integration aims to improve response latency and data privacy for users. The collaboration marks a shift toward local-first AI, potentially reducing reliance on server-side infrastructure for common search tasks.
Covered by 2 sources
- JJon Peddie Research↗Aug 25
- HHacker News↗inferhavenAug 26