Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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.
| Date | Stars |
|---|---|
| 2026-07-24 | 2409 |
| 2026-07-25 | 2409 |
| 2026-07-28 | 2409 |
| 2026-07-30 | 2409 |
| 2026-08-10 | 2423 |
| 2026-08-18 | 2425 |
| 2026-08-19 | 2426 |
| 2026-08-20 | 2429 |
| 2026-08-23 | 2430 |
| 2026-08-25 | 2431 |
| 2026-08-27 | 2432 |
| 2026-08-28 | 2433 |
| 2026-08-29 | 2433 |
| 2026-09-03 | 2434 |
| 2026-09-04 | 2435 |
| 2026-09-06 | 2436 |
| 2026-09-08 | 2437 |
| 2026-09-10 | 2438 |
| 2026-09-14 | 2441 |
| 2026-09-15 | 2443 |
| 2026-09-17 | 2445 |
| 2026-09-20 | 2445 |
Today
— stars today
This week
+7 stars this week
This month
+16 stars this month
Momentum
7.0
growth rate 0.29%/day
# Awesome Model Quantization [](https://awesome.re) Awesome Model Quantization is a curated, continuously updated collection of papers, benchmarks, surveys, and open-source implementations on neural network and model quantization. It spans binary and ternary networks, post-training quantization, quantization-aware training, vector and lattice quantization, low-bit LLMs, multimodal and generative models, KV-cache quantization, low-precision training, and hardware-efficient deployment. ## Quick Navigation - [Research Landscape](#research-landscape) - [Representative Works](#representative-works) - [Benchmarks](#benchmarks) · [Survey Papers](#survey-papers) - [Papers by Year](#papers-by-year)<br> [2026](#2026) · [2025](#2025) · [2024](#2024) · [2023](#2023) · [2022](#2022) · [2021](#2021) · [2020](#2020) · [2019](#2019) · [2018](#2018) · [2017](#2017) · [2016](#2016) · [2015](#2015) · [2014](#2014) - [Books](#books) · [Related Repositories](#related-repositories) · [Researcher Homepages](#researcher-homepages) · [Contributing / Scope](#contributing--scope) ## Research Landscape Model quantization can be organized along five dimensions: - **Optimization:** post-training quantization (PTQ), quantization-aware training (QAT), quantized fine-tuning, data-free methods, and low-precision training. - **Representation:** scalar, vector/codebook, lattice, binary-coded, binary/ternary, and mixed-precision quantization. - **Error reduction:** rotations, outlier smoothing, residual reconstruction, error compensation, and sensitivity-aware methods. - **Quantized tensors:** weights, activations, KV caches, training states, gradients, and communication. - **Models and deployment:** vision, language, multimodal, generative, state space, and graph models, alongside edge and hardware systems. Methods often combine several dimensions, such as PTQ with rotations and vector codebooks. <details> <summary><strong>🔎 Explore the taxonomy and method connections · Click to expand</strong></summary> **Optimization paradigm** **Post-Training Quantization (PTQ)** converts a pretrained model, often with calibration: GPTQ, SmoothQuant, AWQ, OmniQuant, QuaRot, SpinQuant, FlatQuant, BiLLM. **Quantization-Aware Training (QAT)** models quantization during optimization: PACT, LSQ, IR-Net. **Quantized Fine-Tuning / Parameter-Efficient Fine-Tuning (PEFT)** adapts low-bit models: QLoRA, QA-LoRA, LoftQ, IR-QLoRA, L4Q. **Data-Free / Zero-Shot Quantization** avoids original training data, using model statistics or synthetic samples: ZeroQ, Qimera. **Low-Precision Training** also reduces precision in training computation or stored states: INT8/FP8 training, 8-bit Optimizers. **Representation / coding structure** **Scalar quantization** codes individual values; **non-uniform, logarithmic, and floating-point quantization** change the available levels (AdaLog, LLM-FP4). **Vector quantization** jointly codes tuples; **codebook quantization** stores reusable representatives; **product / grouped vector quantization** partitions vectors into groups (GPTVQ, VPTQ, EPQuant). **Lattice quantization** uses structured geometric codebooks (QuIP#, NestQuant, grouped lattice vector quantizers). **Binary-coded quantization** combines binary bases (AnyBCQ); **binary / ternary quantization** constrains values to two / three levels (IR-Net, BiBERT, PT²-LLM). **Mixed precision** allocates different bit widths or formats across tensors or groups (HAWQ, SliM-LLM). **Transformation / error handling** **Rotation / orthogonal transforms** redistribute coordinates (QuaRot, SpinQuant); **outlier smoothing / redistribution** balances quantization difficulty (SmoothQuant, AWQ). **Residual / low-rank reconstruction** models remaining errors or outliers (LQER, SVDQuant); **error compensation** corrects quantization effects (GPTQ, First-Order Error Matters). **Saliency-aware / Hessian-aware quantization** uses importance or curvature to guide precis
Excerpt of 247,747 characters
Read on GitHub
180
51
Xingyu Zheng · Beihang University
24
8
7
5
4
4
Yi Liu · AI Frameworks Engineer @Intel
3
3
2
Jinuk Kim
2
2
2
2
2
2
2
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b22f98dc864717af, topic:quantization, topic:model-compression, name:quantization