microsoft/BitNet
Official inference framework for 1-bit LLMs
Key features
- Inference for 1.58-bit models on CPU and GPU
- Lossless kernels for x86 and ARM CPUs
- Runs a 100B model on a single CPU
- Ships a 2.4B chat model and embedding models
- I2_S conversion kernels for embedding inference on x86
- Category
- Trending Repos
- Who it's for
- People who want to run 1-bit LLMs on their own CPU or GPU.
- Tags
- githubmicrosoftgpuembeddings
- Website
- github.com
- Listed
- 2026-10-12
Frequently asked questions
Is microsoft/BitNet free?
Yes. microsoft/BitNet is open source and free to use.
What is microsoft/BitNet used for?
Official inference framework for 1-bit LLMs. Typical uses: inference for 1.58-bit models on CPU and GPU; lossless kernels for x86 and ARM CPUs; runs a 100B model on a single CPU.
Related in Trending Repos
See all →- addyosmani/agent-skills Engineering skills for AI coding agents, from Addy Osmani.
- anthropics/knowledge-work-plugins Open source plugins for knowledge workers to use in Claude Cowork.
- aquasecurity/trivy Scanner for vulnerabilities, misconfigurations, and secrets.
- AtomicBot-ai/atomic-agent Local-first AI agent that runs open-weight models via llama.cpp.
- axios/axios Promise-based HTTP client for the browser and Node.js.
- bevyengine/bevy Data-driven game engine written in Rust.