| --- |
| tags: |
| - translation |
| - hy-mt |
| - quant |
| - 2bit |
| language: |
| - multilingual |
| base_model: |
| - tencent/HY-MT1.5-1.8B |
| --- |
| |
| <p align="center"> |
| <picture> |
| <source media="(prefers-color-scheme: dark)" srcset="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/logos/angelslim_logo_light.png?raw=true"> |
| <img alt="AngelSlim" src="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/logos/angelslim_logo.png?raw=true" width=55%> |
| </picture> |
| </p> |
| |
| <h3 align="center"> |
| Dedicated to building a more intuitive, comprehensive, and efficient LLMs compression toolkit. |
| </h3> |
|
|
| <p align="center"> |
| 📱 <a href="https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-2bit-GGUF/resolve/main/Hy-MT-demo.apk?download=true">Android Demo</a> | |
| 📣 <a href="https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-2bit-GGUF">GGUF</a> | |
| ✒️ <a href="https://arxiv.org/abs/2602.21233">AngelSlim Report</a> | |
| 📖 <a href="https://angelslim.readthedocs.io/">Documentation</a> | |
| 🤗 <a href="https://huggingface.co/AngelSlim">AngelSlim</a> | |
| 💬 <a href="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/angel_slim_wechat.png?raw=true">WeChat</a> |
| <br> |
| </p> |
|
|
| <p align="center"> |
| <img src="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/HYMT1.5/model_scores.png?raw=true" alt="model_scores" width="80%"> |
| <br> |
| <em>Hy-MT1.5-1.8B translation quality scores. Source: <a href="https://arxiv.org/abs/2512.24092">HY-MT1.5 Technical Report</a></em> |
| </p> |
|
|
| ## 📣 Latest News |
| - [26/04/29] We have released **Hy-MT1.5-1.8B-2bit (574MB)** and **Hy-MT1.5-1.8B-1.25bit (440MB)**, on-device translation models supporting 33 languages, with both weights and GGUF formats available. We also have made an [Android Demo](https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-2bit-GGUF/resolve/main/Hy-MT-demo.apk?download=true) for you to try out. We invite you to give it a spin! 🔥🔥🔥 |
| - [26/02/09] We have released HY-1.8B-2Bit, 2-bit on-device large language model. |
| - [26/01/13] We have released v0.3. We support the training and deployment of Eagle3 for all-scale LLMs/VLMs/Audio models. And we released **Sherry**, the hardware-efficient 1.25-bit quantization algorithm [[Paper]](https://arxiv.org/abs/2601.07892) | [[Code]](https://github.com/Tencent/AngelSlim/tree/sherry/Sherry) |
|
|
| For more detailed information, please refer to [[AngelSlim]](https://github.com/Tencent/AngelSlim) and [[HY-MT]](https://github.com/Tencent-Hunyuan/HY-MT) |
|
|
| ## 🌟 Hy-MT1.5-1.8B-2bit Key Features |
|
|
| - **World-Class Translation Quality** Hy-MT1.5-1.8B-2bit is built upon the Hy-MT1.5-1.8B foundation model, a specialized translation model developed by Tencent Hunyuan Team through a holistic multi-stage training pipeline integrating MT-oriented pre-training, supervised fine-tuning, on-policy distillation, and reinforcement learning. The base model natively supports **33 languages**, **5 dialects/minority languages**, and **1,056 translation directions**. With only 1.8B parameters, it comprehensively outperforms much larger open-source models (e.g., Tower-Plus-72B, Qwen3-32B) and mainstream commercial translation APIs (e.g., Microsoft Translator, Doubao Translator). For full details, please refer to the [HY-MT1.5 Technical Report](https://arxiv.org/abs/2512.24092). |
|
|
|
|
| - **Ultra-Compact 2-bit Quantization** Hy-MT1.5-1.8B-2bit employs industry-leading Stretched Elastic Quantization (SEQ) to quantize model weights to `{-1.5, -0.5, 0.5, 1.5}`, combined with quantization-aware distillation. This compresses the original 3.3GB FP16 model down to just **574MB** while maintaining near-lossless translation quality that surpasses models hundreds of GBs in size. The quantization details are described in the [AngelSlim Technical Report](https://arxiv.org/abs/2602.21233). |
|
|
| - **On-Device Deployment** Optimized for Arm SME2-capable mobile devices (e.g., Apple M4, vivo x300), the 2-bit model enables fast, fully offline translation directly on your phone, no internet connection required. Your data never leaves the device, ensuring complete privacy. |
|
|
| ## 📈 Translation Benchmarks |
|
|
| Performance comparison of different model sizes on the Flores-200 Chinese-Foreign mutual translation benchmark: |
|
|
| <p align="center"> |
| <img src="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/HYMT1.5/flores_model_size.png?raw=true" alt="flores_model_size" width="80%"> |
| <br> |
| <em>Performance of different model sizes on the Flores-200 Chinese-Foreign mutual translation benchmark.</em> |
| </p> |
|
|
| ## ⚡ Speed Demo |
|
|
| Speed comparison of the 2-bit model on SME2 and Neon kernels: |
|
|
| <p align="center"> |
| <img src="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/HYMT1.5/sme2_2bit.gif?raw=true" alt="sme2_2bit_speed" width="60%"> |
| <br> |
| <em>Speed comparison of the 2-bit model on SME2 and Neon kernels.</em> |
| </p> |
|
|
| ## 📱 Demo |
|
|
| We provide a ready-to-use Android demo APK for offline translation. The app features a **background word extraction mode** that works across any app on your phone — browse emails, webpages, or chat messages and get instant translations without switching apps. No network required, no data collection, one-time download for permanent use. |
|
|
| **Download Demo:** |
|
|
| https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-1.25bit-GGUF/resolve/main/Hy-MT-demo.apk |
|
|
| ### Translation Demo |
|
|
| <p align="center"> |
| <img src="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/HYMT1.5/app_demo.gif?raw=true" alt="app_demo" width="40%"> |
| <br> |
| <em> Demo device: Snapdragon 865, 8GB RAM.</em> |
| </p> |
|
|
| ### Background Word Extraction Mode |
|
|
| <p align="center"> |
| <img src="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/HYMT1.5/demo2.gif?raw=true" alt="demo2" width="40%"> |
| <br> |
| <em>Demo device: Snapdragon 7+ Gen 2, 16GB RAM.</em> |
| </p> |
|
|
| ## 📥 Download Links |
|
|
| - 2-bit model weights: https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-2bit |
| - 2-bit model GGUF: https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-2bit-GGUF |
| - 1.25-bit model weights: https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-1.25bit |
| - 1.25-bit model GGUF: https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-1.25bit-GGUF |
| - Demo: https://huggingface.co/AngelSlim/Hy-MT1.5-1.8B-1.25bit-GGUF/resolve/main/Hy-MT-demo.apk |
|
|
|
|
| ## 📄 Technical Reports |
| - HY-MT1.5 Technical Report: https://arxiv.org/abs/2512.24092 |
| - AngelSlim Technical Report: https://arxiv.org/abs/2602.21233 |
| - Sherry Paper: https://arxiv.org/abs/2601.07892 |
|
|
| ## 📝 License |
|
|
| The code for this project is open-sourced under the [License for AngelSlim](LICENSE). |
|
|
| ## 🔗 Citation |
|
|
| ```bibtex |
| @article{angelslim2026, |
| title={AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression}, |
| author={Hunyuan AI Infra Team}, |
| journal={arXiv preprint arXiv:2602.21233}, |
| year={2026} |
| } |
| |
| @misc{zheng2025hymt, |
| title={HY-MT1.5 Technical Report}, |
| author={Mao Zheng and Zheng Li and Tao Chen and Mingyang Song and Di Wang}, |
| year={2025}, |
| eprint={2512.24092}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL}, |
| url={https://arxiv.org/abs/2512.24092}, |
| } |
| ``` |
|
|
| ## 💬 Technical Discussion |
|
|
| * AngelSlim is continuously iterating and new features will be released soon. If you have any questions or suggestions, please open an issue on [GitHub Issues](https://github.com/Tencent/AngelSlim/issues) or join our [WeChat discussion group](https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/angel_slim_wechat.png?raw=true). |
|
|
