Developed by Microsoft Research, BitNet b1.58 2B4T is the first open-source, native 1-bit large language model (LLM) in which every parameter is ternary (i.e., -1, 0, 1), at a 2-billion parameter scale. Trained on a corpus of 4 trillion tokens, this model demonstrates that native 1-bit LLMs can achieve performance comparable to leading open-weight, full-precision models of similar size, while offering substantial advantages in computational efficiency, including substantially reduced memory footprint, energy consumption, and decoding latency.

Microsoft researchers have demonstrated that BitNet b1.58 2B4T achieves performance on par with leading open-weight, full-precision LLMs of similar size, while offering significant advantages in computational efficiency, including substantially reduced memory footprint, energy consumption, and decoding latency. To facilitate further research and adoption, the model weights have been released along with open-source inference implementations for both GPU and CPU architectures.