Microsoft researchers claim to have developed the first 1-bit large language model with 2 billion parameters. The model, BitNet b1.58 2B4T, can run on commercial CPUs such as Apple’s M2.

“We introduce BitNet b1.58 2B4T, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale,” the Microsoft researchers wrote.

The term “1-bit LLMs” is more symbolic than literal. These models employ ternary weights rather than binary ones, allowing reduced memory usage and faster computation without sacrificing too ...