做多语言翻译的开发者终于有了能本地跑的开源模型——Hy-MT2 的 1.8B 版本比微软 API 还强，且量化后仅 440MB，手机芯片就能推理，建议直接下载试试。
腾讯混元发布 Hy-MT2 开源多语言翻译模型，支持 33 种语言无缝互译。7B 和 30B-A3B 版本在多项翻译任务上超越参数大数十倍的模型，轻量 1.8B 版本甚至优于微软等商业 API。模型采用腾讯 AngelSlim 1.25-bit 极致量化，仅需 440MB 存储，可在主流移动芯片上本地推理，速度比 Hy-MT1.5 快 1.5 倍。项目已在 GitHub、Hugging Face 等平台开源。
🚀 Introduce Hy-MT2: New Open-Source Multilingual Translation Model We proudly launch our new Hy-MT...
🚀 Introduce Hy-MT2: New Open-Source Multilingual Translation Model We proudly launch our new Hy-MT2 translation model and the Tencent Hy Translation mini-program! Hy-MT2 is a powerful multilingual model supporting seamless translation across 33 languages — and it's fully open-source! It's 7B and 30B-A3B models achieve state-of-the-art performance among all open-source models on various translation tasks, surpassing models with dozens of times more parameters. The lightweight 1.8B model even outperforms mainstream commercial APIs like Microsoft and so on. Powered by Tencent AngelSlim 1.25-bit extreme quantization, it needs just 440MB storage and enables effortless local inference on mainstream mobile chips — with 1.5x faster speed vs. Hy-MT1.5. Open-source AI translation just got way smarter, faster, and more accessible! 🌏 Project Page aistudio.tencent.com/llm/zh?tabInde… jB Hugging Face huggingface.co/collections/te… Du Modelscope modelscope.cn/collections/Te… po Github github.com/Tencent-Hunyua… OX 💬 12 🔄 26 ❤️ 168 👀 14396 📊 57 ⚡