BitNet b1.58 2B4T Technical Report
This work addresses the computational inefficiency of large language models for researchers and practitioners by providing an open-source, efficient alternative.
The authors introduced BitNet b1.58 2B4T, a 1-bit large language model with 2 billion parameters trained on 4 trillion tokens, which achieves performance comparable to full-precision models of similar size while offering significant improvements in computational efficiency, such as reduced memory, energy, and latency.
We introduce BitNet b1.58 2B4T, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale. Trained on a corpus of 4 trillion tokens, the model has been rigorously evaluated across benchmarks covering language understanding, mathematical reasoning, coding proficiency, and conversational ability. Our results demonstrate 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 are released via Hugging Face along with open-source inference implementations for both GPU and CPU architectures.