BitNet b1.58 2B4T Technical Report

Shuming Ma, Hongyu Wang, HUANG SHAOHAN, Xingxing Zhang, Ying Hu, Ting Song, Yan Xia, Furu Wei

BitNet b1.58 2B4T Technical Report: 87 upvotes on Hugging Face Daily Papers, #1 of 16 papers on 2025-04-17. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.