腾讯混元开源 Hy-MT1.5-1.8B-1.25bit 翻译模型，该模型仅 440MB，可在手机完全离线运行，支持 33 种语言。1.8B 参数在标准基准上匹配商业翻译 API 和 235B 规模模型，量化到 1.25-bit 后内存从 3.3GB（FP16）降至 440MB，比之前 1.67-bit 方案小 25%、快约 10%，且无精度损失。
1.8B 翻译模型量化到 1.25bit 后仅 440MB，可在手机离线运行，为端侧模型压缩提供参考。
We're open-sourcing Hy-MT1.5-1.8B-1.25bit — a 440MB translation model that runs fully offline on your phone, supports 33 languages, and outperforms Google Translate.
At 1.8B parameters, it matches commercial translation APIs and 235B-scale models on standard benchmarks. By quantizing to 1.25-bit, memory drops from 3.3GB (FP16) to 440MB — 25% smaller and ~10% faster than prior 1.67-bit approaches, with no accuracy loss.
Covers 33 languages, 5 dialects, and 1,056 translation directions including minority languages like Tibetan and Mongolian.
Our translation model has won 30 first-place rankings in international MT competitions and is already deployed across multiple Tencent products.🏆
📲Demo APK (Android): huggingface.co/AngelSlim/Hy-…
🤗Hugging Face:: huggingface.co/AngelSlim/Hy-…
🔗GitHub: github.com/tencent/AngelSlim
📄Paper: arxiv.org/abs/2601.07892
来源：@TencentHunyuan · x.com