Awesome-Model-Quantization
A running list of low-bit model quantization research papers from 2020 through 2026, organized by year, covering LLMs, vision-language-action models, and mixture-of-experts.
Awesome-Model-Quantization collects low-bit quantization papers for deep neural networks published between 2020 and 2026, organized into a survey section and per-year paper lists. Entries span topics such as mixed-precision quantization for long-context inference, quantization for mixture-of-experts models, quantization-enhanced reinforcement learning for LLMs, vision-language-action model quantization, quantization for visual autoregressive and video-matting models, LoRA-based adaptation of already-quantized LLMs, and ternary and binary-coded quantization schemes, with links to code where the authors released it.
Each entry names its publication venue, such as a major machine-learning conference, and links to the paper and, where available, its code.