Show HN: WebGPU enables local LLM in the browser – demo site with AI chatandreinwald.github.io145 points·by andreinwald·hace 12 meses·54 comments
andreinwald·hace 12 meses·discussIt works on small Llama-3.2-1B model, specially for less powerfull GPU devices
andreinwald·hace 12 meses·discussModel used: Llama 3.2 1B (small). Quality hould be similar with running Ollama app with same small model.
andreinwald·hace 12 meses·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.