---
title: Qwen2.5 0.5B Browser Chat
emoji: 💬
colorFrom: purple
colorTo: blue
sdk: static
app_file: index.html
short_description: Private browser chat with Qwen2.5 0.5B
models:
  - Qwen/Qwen2.5-0.5B-Instruct
  - onnx-community/Qwen2.5-0.5B-Instruct
---

# Qwen2.5 0.5B — private browser chat

This free static Space runs a quantized conversion of
[`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
directly in the visitor's browser using Transformers.js. Prompts and responses
stay on the device; there is no inference server.

The first use downloads and caches the model (roughly a few hundred MB).
WebGPU is used when the browser supports it, with WebAssembly as a fallback.