Git Stars Git Stars

#post-training-quantization Repositories

Discover 12 active open source GitHub repositories tagged with #post-training-quantization, accumulating 21,589 total stars (averaging 1,799 stars per project). Leading this topic is NVIDIA/Model-Optimizer with 5,646 stars.

12
Total Repositories
21,589
Total Stars
1,799
Avg Stars/Repo
Programming Languages: Python
1
NVIDIA/Model-Optimizer

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

NVIDIA
โญ 5,646 Python ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-04-23
2
intel/neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

intel
โญ 2,733 Python ๐Ÿ‘ค intel Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2020-07-21
3
AI-Efficiency/Awesome-Model-Quantization

A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient deployment.

AI-Efficiency
โญ 2,471 ๐Ÿ‘ค AI-Efficiency Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2018-10-18
4
666DZY666/micronet

micronet, a model compression and deploy lib. compression: 1ใ€quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)ใ€Low-Bit(โ‰ค2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2ใ€ pruning: normalใ€regular and group convolutional channel pruning; 3ใ€ group convolution structure; 4ใ€batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/in

666DZY666
โญ 2,270 Python ๐Ÿ‘ค 666DZY666 User ๐Ÿ• Updated 2025-05-06 ๐Ÿ“… Created 2019-12-04
5
IST-DASLab/gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

IST-DASLab
โญ 2,241 Python ๐Ÿ‘ค IST-DASLab Organization ๐Ÿ• Updated 2024-03-27 ๐Ÿ“… Created 2022-10-19
6
mit-han-lab/smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

mit-han-lab
โญ 1,576 Python ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2024-07-12 ๐Ÿ“… Created 2022-11-17
8
alibaba/TinyNeuralNetwork

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

alibaba
โญ 881 Python ๐Ÿ‘ค alibaba Organization ๐Ÿ• Updated 2026-03-03 ๐Ÿ“… Created 2021-11-02
9
nunchaku-ai/deepcompressor

Model Compression Toolbox for Large Language Models and Diffusion Models

nunchux-ai
โญ 799 Python ๐Ÿ‘ค nunchux-ai Organization ๐Ÿ• Updated 2025-08-14 ๐Ÿ“… Created 2024-05-06
10
SqueezeAILab/SqueezeLLM

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

SqueezeAILab
โญ 710 Python ๐Ÿ‘ค SqueezeAILab Organization ๐Ÿ• Updated 2024-08-13 ๐Ÿ“… Created 2023-06-12
11
microsoft/VPTQ

VPTQ, A Flexible and Extreme low-bit quantization algorithm

microsoft
โญ 683 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-08-04 ๐Ÿ“… Created 2024-08-13

Frequently Asked Questions

1

What is the most popular #post-training-quantization repository on GitHub?

The top ranked open source #post-training-quantization project on GitHub is NVIDIA/Model-Optimizer with 5,646 stars. A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

2

Which programming languages are most used in #post-training-quantization repositories?

Among the top ranked #post-training-quantization projects on GitHub, the most common programming languages are Python.

3

How is the #post-training-quantization repository ranking calculated?

We track 12 active open source repositories tagged with #post-training-quantization (500+ stars), totaling 21,589 stars with an average of 1,799 stars per repository. Rankings update daily from the GitHub API.