Run efficient AI models that use less memory while maintaining quality for tasks like embedding.
From the README
git clone --recursive https://github.com/microsoft/BitNet.git cd BitNet
- 1.42x to 2.28x speedup over F16 on BitNet-embedding-0.6B prefill (8 threads)
- 1.32x to 1.74x speedup over F16 on BitNet-embedding-270M prefill (8 threads)
- Supports I2S conversion with optimized kernels on x86 CPUs
- Lossless inference with 2 bits per weight
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeOfficial inference framework for 1-bit LLMs
BitNet has 40.2k stars on GitHub. It has been forked 3.7k times. BitNet is written mainly in C++. It has been in active development since 2024. BitNet is available under the MIT license.
What is BitNet?
Official inference framework for 1-bit LLMs
Is BitNet open source?
BitNet is an open-source project. It is released under the MIT license.
Is BitNet free?
Yes. BitNet is free and open source — you can use, modify and self-host it.
What license does BitNet use?
BitNet is available under the MIT license.
What language is BitNet written in?
BitNet is written mainly in C++.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/microsoft-bitnet.html)
