m96-chan/0xBitNet
Run BitNet b1.58 ternary LLMs with WebGPU — in browsers and native apps
This project allows developers to integrate small, efficient AI language models directly into web applications or desktop software. It takes pre-trained BitNet b1.58 or Falcon-E models as input and outputs generated text, enabling features like real-time chat or content summarization without needing a dedicated server. This is for software developers creating applications that require on-device AI text generation.
Available on npm.
Use this if you are a developer looking to add fast, locally-run AI language model capabilities to your browser-based or native applications.
Not ideal if you need to run large, complex AI models or require extensive customization beyond what's offered by the supported BitNet architecture.
Stars
10
Forks
—
Language
TypeScript
License
MIT
Category
Last pushed
Mar 08, 2026
Monthly downloads
206
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/m96-chan/0xBitNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huawei-csl/SINQ
Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method...
SILX-LABS/QUASAR-SUBNET
QUASAR is a long-context foundation model and decentralized evaluation subnet built on Bittensor,
stackblogger/bitnet.js
BitNet.Js - A node.js implementation of the microsoft bitnet.cpp inference framework.
AnswerDotAI/cold-compress
Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking...
FMInference/H2O
[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.