Follow + comment **GPU** and I’ll send you the full install guide. 👇 Big Tech spends BILLIONS on GPUs… but someone just ran a **744B parameter AI model on a laptop. 🤯** No NVIDIA GPU. No cloud. Completely offline. The project is called Colibri and instead of loading the entire model into memory, it keeps only what it needs in RAM and streams the rest from your SSD. That means: → Massive AI models running locally → No API costs → Your data stays on your machine → OpenAI-compatible endpoint → No expensive GPU required The catch? You’ll need around **370GB of storage.** 😅 Local AI is getting seriously interesting. #AI #ArtificialIntelligence #LocalAI #OpenSourceAI #LLM #AITools #Coding - @build.with.alan