bitnet.cpp

bitnet.cpp is the official inference framework for 1-bit LLMs such as BitNet b1.58. It provides optimized kernels for inference of 1.58-bit models on CPU and GPU, with NPU support stated as coming next. The repository includes documentation and setup scripts, and the project is released under the MIT license.

GitHub repo Directory import
0 shouts Added Sep 23, 2026 github.com
github.com/microsoft/BitNet
bitnet.cpp website preview

Limitations

Links

Tags