Y Hacker News new | ask | show | jobs

user: alexandercheema created: 2024-07-16 karma: 168 submissions: 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Kimi K2.5 on 2 Mac Studios (<$20K) running at 24 TPS 6 points | 4 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference 8 points | 1 comments Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference 5 points | 0 comments 0 points | 0 comments Meta AI: "The Future of AI Is Open Source and Decentralized" 214 points | 111 comments Two MacBooks is All You Need: Running Llama 3 405B using Apple MLX and Exo 11 points | 2 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments