ChatLLM Web

English / 简体中文

🗣️ Chat with LLM like Vicuna totally in your browser with WebGPU, safely, privately, and with no server. Powered By web-llm.

Try it now

Features

• 🤖 Everything runs inside the browser with no server support and is accelerated with WebGPU.

• ⚙️ Model runs in a web worker, ensuring that it doesn't block the user interface and providing a seamless experience.

• 🚀 Easy to deploy for free with one-click on Vercel in under 1 minute, then you get your own ChatLLM Web.

• 💾 Model caching is supported, so you only need to download the model once.

• 💬 Multi-conversation chat, with all data stored locally in the browser for privacy.

• 📝 Markdown and streaming response support: math, code highlighting, etc.

• 🎨 responsive and well-designed UI, including dark mode.

Instructions

• 🌐 To use this app, you need a browser that supports WebGPU, such as Chrome 113 or Chrome Canary. Chrome versions ≤ 112 are not supported.

• 💻 You will need a GPU with about 6.4GB of memory. If your GPU has less memory, the app will still run, but the response time will be slower.

• 📥 The first time you use the app, you will need to download the model. For the Vicuna-7b model that we are currently using, the download size is about 4GB. After the initial download, the model will be loaded from the browser cache for faster usage.

• ℹ️ For more details, please visit mlc.ai/web-llm

Roadmap

• [✅] LLM: using web worker to create an LLM instance and generate answers.

• [✅] Conversations: Multi-conversation support is available.

• [] Desktop: Build a desktop version with Tauri, which will use system cache (not just browser cache) and run locally and offline.

• [] UI: Dark and Light Theme.

Deploy to Vercel

1. Click , follow the instructions, and finish in just 1 minute.
2. Enjoy it 😊

Development

git clone https://github.com/Ryan-yang125/ChatLLM-Web.git
cd ChatLLM-Web
npm i
npm run dev

Screenshots

LICENSE

MIT