Hy-MT2-30B-A3B is Tencent Hunyuan's largest translation model, a sparse mixture-of-experts architecture (30B total parameters, 3B active, 128 routed plus 1 shared expert) supporting 33 languages, released open-weight (Apache 2.0) alongside the smaller 1.8B and 7B dense Hy-MT2 variants. In fast-thinking mode it outperforms larger open-source general models such as DeepSeek-V4-Pro and Kimi K2.6 on translation benchmarks, making it the pick for high-quality business and domain-specific translation where the dense variants fall short.
Тариф стоимости
0.1x
Контекст
8K
Выпуск
20 авг. 2026 г.
Ввод
Text
Вывод
Text
Поддержка
РассуждениеВызов инструментовСтруктурированный вывод
Последние новости о Hy-MT2-30B-A3B
Свежие статьи и публикации сообщества со ссылками на первоисточники.
- Trump Approved 879,868 Nvidia, AMD AI Chips for China; Alibaba, Tencent, Baidu and BYD Among BuyersInternational Business Times Singapore

- Tencent Hy4 FlashHacker News17527
Oracle CANCELS AI CHIP LEASING CONTRACT with Tencent - $7 Billion Destroyed by Trump PoliciesEli the Computer Guy88,165


Tencent launches Hy4Hacker News954