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.
Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy [ICML 2026]
| Date | Stars |
|---|---|
| 2026-07-31 | 627 |
| 2026-08-02 | 627 |
| 2026-08-06 | 627 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[](https://icml.cc)
[](https://arxiv.org/abs/2509.22944)
[](https://opensource.org/licenses/Apache-2.0)
[](https://github.com/huawei-csl/SINQ/stargazers)
[](https://huggingface.co/huawei-csl)
[](https://huggingface.co/docs/transformers/main/quantization/sinq)
<table border="0" cellspacing="0" cellpadding="0">
<tr>
<td><img src="imgs/logo_icml.png" alt="SINQ Logo" width="160"></td>
<td style="vertical-align: middle;"><h1>SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLMs</h1></td>
</tr>
</table>
> ⚡️ **A fast, plug-and-play, model-agnostic quantization technique** delivering **state-of-the-art performance** for Large Language Models **without sacrificing accuracy.**
> 💡 **Want to run a large model on your GPU but don’t have enough memory?** With **SINQ**, you can deploy models that would otherwise be too big **drastically reducing memory usage while preserving LLM quality.**
> ⏱️ SINQ quantizes **Qwen3-14B** in just **~21 sec** and **DeepSeekV2.5-236B** in **~5 min**
---
## News:
🆕 [01/05/2026] **SINQ was accepted and will be presented at ICML 2026! 🤗**
See you in Seoul! 🇰🇷 (More info [here](https://icml.cc/virtual/2026/poster/63404))
🆕 [18/02/2026] **SINQ is now integrated into HF Transformers! 🤗**
> **You can now use SINQ in 🤗 Transformers in a super simplified way** thanks to our **SinqConfig** compatible with **HF AutoModelForCausalLM()**!
More information directly on the HF website [here](https://huggingface.co/docs/transformers/main/quantization/sinq)!
🆕 [10/02/2026] **A first GGUF model with pre-SINQ! 🤗**
> **First GGUF model using pre-SINQ available in our collection **[huawei-csl/PreSINQ GGUF](https://huggingface.co/collections/huawei-csl/presinq-gguf)** collection!**
> Thanks to our new _pre-SINQ_ algorithm (see details [here](#5-how-to-reproduce-paper-results)), we can finally bring the strengths of SINQhorn normalization together with the advantages of GGUF quantization! Many more models coming soon!
>**You can vote** for the next SINQ GGUF model **[here](https://github.com/huawei-csl/SINQ/discussions/21)**!
---
## 🚀 Welcome to the **official SINQ repository**!
**SINQ** (Sinkhorn-Normalized Quantization) is a **novel, fast and high-quality quantization method** designed to make any Large Language Models **smaller** while keeping their accuracy almost intact.
### 🔍 What You’ll Find Here
- [1. How does SINQ work?](#1-how-does-sinq-work)
- [2. Why should I use SINQ?](#2-why-should-i-use-sinq)
- <u>[3. Quantize (and save) any LLM with SINQ](#3-quantize-any-llm-with-sinq)</u>
- [4. Run pre-quantized SINQ models from Hugging Face](#4-run-pre-quantized-sinq-models-from-hugging-face)
- [5. How to reproduce paper results](#5-how-to-reproduce-paper-results)
- [6. Pre-SINQ: SINQhorn normalization for GGUFs (and more)!](#6-pre-sinq-sinqhorn-normalization-for-ggufs-and-more)
- [7. Ongoing updates on new features and integrations](#7-ongoing-updates-on-new-features-and-integrations)
- [8. How to Cite This Work](#8-how-to-cite-this-work)
- [9. Related Repositories](#9-related-repositories)
#### 📊 Feature Comparison: SINQ vs HQQ _(calibration-free)_ and A-SINQ vs AWQ _(calibrated)_
| Feature | **SINQ** | **HQQ** | **A-SINQ** | **AWQ** |
|------------|:--------:|:--------:|:----------:|:-------:|
| 🎯 Calibration | Calibration-free | Calibration-free | Calibrated | CalibExcerpt of 21,037 characters
Read on GitHub
100
14
7
2
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:df83a6fd22fd70d2, topic:large-language-models, topic:qwen
matched fp:df83a6fd22fd70d2, topic:quantization, desc:quantization