microsoft/BitNet
Official inference framework for 1-bit LLMs
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
[](https://opensource.org/licenses/MIT) [](https://huggingface.co/collections/microsoft/bitnet) [](https://arxiv.org/abs/2502.11880) [](https://demo-bitnet-h0h8hcfqeqhrf5gf.canadacentral-01.azurewebsites.net/) [](https://github.com/microsoft/BitNet/blob/main/gpu/README.md) 📰 News 07/23/2026: 📣 We released VibeASR.cpp — a real-time multilingual ASR inference engine on CPU using BitNet I2S quantization, achieving RTF Code] [Models] [Report] 07/20/2026: 📣 We released BitNet-embedding-0.6B and BitNet-embedding-270M on Hugging Face — the first 1-bit embedding models that deliver competitive embedding quality with significantly faster inference on CPUs. 07/16/2026: 📣 Released BitNet Embeddings 0.6B/270M: I2S Conversion and Inference Optimization — detailed guide for converting and running BitNet embedding models with optimized I2S kernels. 01/15/2026: 📣 Released BitNet CPU Inference Optimization — parallel kernel implementations with configurable tiling and embedding quantization support, achieving 1.15x to 2.1x additional speedup over the original implementation. 05/20/2025: 📣 Released BitNet Official GPU inference kernel — extending 1-bit inference beyond CPUs. 04/14/2025: 📣 Released BitNet Official 2B Parameter Model on Hugging Face — the first official BitNet b1.58 model trained with 4T tokens. 02/18/2025: 📑 Bitnet.cpp: Efficient…
Read the full README ↗ · Preview checked 2026-10-27T00:14:16.689Z
Inside the original README — Document outline
- bitnet.cpp
- Overview
- Model Releases
- 1. BitNet-b1.58-2B-4T - 1-bit Large Language Model
- 2. BitNet-embedding-0.6B - 1-bit Embedding Model
- 3. BitNet-embedding-270M - Lightweight 1-bit Embedding Model
- Supported Models
- Installation
- Requirements
- Build from source
- Usage
- Basic usage
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
- ![License: MIT
- BitNet Embeddings 0.6B/270M: I2S Conversion and Inference Optimization
- BitNet CPU Inference Optimization
- BitNet Official GPU inference kernel
- Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
- 1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs
- The-Era-of-1-bit-LLMs: Training Tips, Code, FAQ
- CPU
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Official inference framework for 1-bit LLMs
Repository facts
- Owner
- microsoft
- Primary language
- C++
- Stars
- 40,734
- Forks
- 3,796
- Open issues + pull requests
- 337
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2024-08-05T09:07:38.000Z
- Last push
- 2026-07-27T05:52:06.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-12T12:05:20.394Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.