🚀 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: https://t.co/eRkw3JLJjB
Hugging Face: https://t.co/4J8gzMdcDu
Modelscope: https://t.co/xh5vEYkHpo
Github:
One More Thing.
We are thrilled to announce that Tencent Hy is officially collaborating with the WMT26 organizers on the Preliminary Video Subtitle Translation Competition!
👉Join here: https://t.co/ToBl9njXIV
Powered by our advanced Hy-MT series models, you can also take part in the General Machine Translation Competition.
📷 Join here: https://t.co/ZoradGSlpy
Top participants have the chance to win special grand prizes! We warmly invite researchers, developers, AI enthusiasts, and everyone passionate about machine translation to join us.
Together, let’s push the boundaries of AI and drive the future of machine translation technology forward!
Don’t miss this incredible opportunity — register and participate today! #WMT26 #Hy #MachineTranslation #AIInnovationWe look forward to seeing your submissions!
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
Why it matters
This gives builders an on-device translation path that no longer requires a commercial API call. The 1.8B variant puts 440MB of weights on phone-class silicon, with larger open variants available when quality matters more than footprint.
