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.
Taux de coût
0.1x
Contexte
8K
Date de sortie
20 août 2026
Entrée
Text
Sortie
Text
Prise en charge
RaisonnementAppel d'outilsSorties structurées
Dernières actualités sur Hy-MT2-30B-A3B
Articles récents et publications de la communauté, avec des liens vers leurs sources d'origine.
- 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