We're excited to announce the the open-source release of Hunyuan-MT-7B, our latest translation model that just won big at WMT2025! 🚀🏆 Hunyuan-MT-7B is a lightweight 7B model that's a true powerhouse. It dominated the competition by winning 30 out of 31 language categories, outperforming much larger models under strict open-source and public-data constraints. On the widely-used Flores200 benchmark, its performance rivals closed-source models like GPT-4.1.🌍💬 Why is this a game-changer? 🔹Unmatched Efficiency: The 7B model delivers lightning-fast inference, processing more translation requests on the same hardware. 🔹Deployment Flexibility: It's cost-effective and can be deployed on a wide range of hardware, from high-end servers to edge devices. 🔹Broad Language Support: It supports 33 languages and 5 minority languages, providing comprehensive coverage. But that's not all. We're also open-sourcing Hunyuan-MT-Chimera-7B, the industry's first open-source integrated translation model. It intelligently refines translations from multiple models to deliver more accurate and professional results for specialized use cases. Download and deploy it for your next project! 👉Try it now: https://hunyuan.tencent.com/modelSquare/home/list 🔗Code: https://github.com/Tencent-Hunyuan/Hunyuan-MT/ 📄Technical Report: https://github.com/Tencent-Hunyuan/Hunyuan-MT/blob/main/Hunyuan_MT_Technical_Report.pdf 🤗Hugging Face: https://huggingface.co/tencent/Hunyuan-MT-7B 🔧AngelSlim: https://github.com/Tencent/AngelSlim
