tiiuae/onebitllms

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Accessible large language models via k-bit quantization for PyTorch.

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Official inference framework for 1-bit LLMs

Official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 2026)

Python package for LLM compression

An Efficient Compression Framework for LLM

Training LLMs with QLoRA + FSDP

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture