alexandercheema

Recent Submissions

1. 1. ▲ Kimi K2.5 on 2 Mac Studios (<$20K) running at 24 TPS (twitter.com) 6 points · 8 months ago · 4 comments
2. 2. ▲ Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference (twitter.com) 8 points · 11 months ago · 1 comment
3. 3. ▲ Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference (blog.exolabs.net) 5 points · 11 months ago · 0 comments
4. 4. ▲ Meta AI: "The Future of AI Is Open Source and Decentralized" (twitter.com) 214 points · 2 years ago · 111 comments
5. 5. ▲ Two MacBooks is All You Need: Running Llama 3 405B using Apple MLX and Exo (twitter.com) 11 points · 2 years ago · 2 comments