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