AI Hub

AI Chat

Chat with a small language model running entirely in your browser — no server, no upload, fully private. Powered by Qwen2.5-0.5B.

Powered by Qwen2.5-0.5B — runs in your browser, no server or upload. Requires a desktop browser with WebGPU support. Model download may be large (≈400 MB).

How to use

  1. Type your question or message in the input box.
  2. Click Send — the model loads and runs in your browser.
  3. The response streams in real time; click Clear to start a new chat.

Examples

  • Ask a general knowledge question and get an instant answer.
  • Brainstorm ideas or get a quick summary of a topic.
  • Test the limits of a small on-device language model.

About the Model

Source: onnx-community/Qwen2.5-0.5B-Instruct

License: Apache 2.0

브라우저 로컬 LLM — transformers.js WebGPU, ~483MB(데스크톱 opt-in 용량정책).