General-Instinct/InstinctRazor

Python package for LLM compression

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

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

State-of-the-art LLM compression, built for production inference with vLLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852

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

Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization

Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input a target size and the toolchain will create a GGUF recipe tuned to your hardware within seconds — flexible model sizing and lowest achievable perplexity/kld for GGUF enthusiasts seeking precise and automated dynamic quant production.

Awesome LLM compression research papers and tools.