---
title: EdgeRazor Playground
emoji: 🚀
colorFrom: blue
colorTo: gray
sdk: gradio
sdk_version: 6.5.1
python_version: 3.12.2
app_file: app.py
pinned: true
license: apache-2.0
---

<div align="center">
  <br/>
  <img src="https://raw.githubusercontent.com/zhangsq-nju/EdgeRazor/main/asset/Logo-full.png" alt="EdgeRazor Logo" width="60%">
  <h3>
    Lightweight Framework for Edge AI
  </h3>

  <p>
    <a href="https://arxiv.org/abs/2605.04062" target="_blank">
      <img src="https://img.shields.io/badge/arXiv-EdgeRazor-b31b1b?style=flat&logo=arxiv" alt="arXiv EdgeRazor">
    </a>
    <a href="https://github.com/zhangsq-nju/EdgeRazor" target="blank">
      <img src="https://img.shields.io/badge/GitHub-EdgeRazor-blue?style=flat&logo=github" alt="GitHub EdgeRazor">
    </a>
  </p>

  <h5>
    ✨ If you like our project, please consider giving us ❤️.
  </h5>
</div>

## EdgeRazor Playground

A CPU-friendly chatbot powered by **[Qwen3-EdgeRazor-nbit](https://huggingface.co/collections/zhangsq-nju/edgerazor-nbit)**, running locally via [llama.cpp](https://github.com/ggerganov/llama.cpp). Displays real-time efficiency metrics (output tokens, time, decoding throughput) per turn.

## Dependencies

- [llama-cpp-python](https://abetlen.github.io/llama-cpp-python/whl/cpu/llama-cpp-python)
- Qwen3-EdgeRazor-nbit gguf files:
  - [Qwen3-0.6B-EdgeRazor-GGUF](https://huggingface.co/zhangsq-nju/Qwen3-0.6B-EdgeRazor-GGUF)
  - [Qwen3-1.7B-EdgeRazor-GGUF](https://huggingface.co/zhangsq-nju/Qwen3-1.7B-EdgeRazor-GGUF)