hannes-sistemica/browser-llm-webgpu
Proof of concept for a reasoning model that runs locally in your browser with WebGPU acceleration
This project offers a way to run a reasoning AI model directly within your web browser, allowing you to generate text or get answers without sending any data to external servers. It takes your text prompts as input and provides AI-generated responses, all computed locally on your device. This is ideal for anyone who needs quick, private AI assistance directly from their browser, especially those in privacy-sensitive fields.
No commits in the last 6 months.
Use this if you need a privacy-focused AI assistant for text generation or reasoning tasks that operates entirely within your web browser, even offline.
Not ideal if you need a highly complex or custom AI model, or if you're looking for a development framework to integrate AI into a larger application.
Stars
18
Forks
4
Language
HTML
License
—
Category
Last pushed
Jan 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/hannes-sistemica/browser-llm-webgpu"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mlc-ai/web-llm
High-performance In-browser LLM Inference Engine
e2b-dev/desktop
E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can...
geekjr/quickai
QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art...
Azure-Samples/llama-index-javascript
This sample shows how to quickly get started with LlamaIndex.ai on Azure 🚀
AkagawaTsurunaki/zerolan-core
ZerolanCore integrates many open-source, locally deployable AI models, and aims to integrate a...