SNU-ARC/any-precision-llm

Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).

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

Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors export, validated on Qwen3.6-35B-A3B MoE with MTP speculative decoding.

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

LLM quantization optimizer

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the hardware you already own.

Statistically-Lossless Quantization of Large Language Models

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

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.