Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
⚡️ Haha! I am planning to bring OpenAI in-house! 🖥️ Snagging a pre-loved Mac Studio to become my offline AI powerhouse! 💪 I am talking Qwen2, Llama-3, Yi-1.5, and Gemma – all the cool kids of the SLM world, ready to party on one machine! Lab squad, assemble! 🔥 https://t.co/p62ztU2bdp
Speed running my home AI cluster running distributed inference across 2 MacBooks and 2 Mac Minis. @exolabs_ displays a real-time network topology as devices discover each other over the local network. Code is open source 👇 https://t.co/RhKFFlJ5YX
In an era of digital dependence, imagine having a powerful AI assistant at your fingertips, even during internet outages or power disruptions. This article explores the feasibility and benefits of building your own home data center to run open-source large language models,
New software called Exo enables users to run a private AI cluster at home using networked devices such as smartphones, tablets, and computers. This software allows for distributed inference across multiple devices, including MacBooks and Mac Minis, with setup taking as little as 60 seconds even on clean installations without Python. Exo supports running AI models like Llama 3 and provides real-time network topology visualization as devices automatically discover each other on the local network. Users can interact with the cluster using the ChatGPT web interface. The code for Exo is open source, making it accessible for users to build their own home data centers to run open-source large language models.
