Show HN: WebGPU enables local LLM in the browser – demo site with AI chatandreinwald.github.io145 points·by andreinwald·12 tháng trước·54 comments
andreinwald·12 tháng trước·discussIt works on small Llama-3.2-1B model, specially for less powerfull GPU devices
andreinwald·12 tháng trước·discussModel used: Llama 3.2 1B (small). Quality hould be similar with running Ollama app with same small model.
andreinwald·12 tháng trước·discussOn my Android device works pretty fast.But keep in mind that it's small Llama-3.2-1B model, specially for less powerfull GPU.