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.
Fascia di costo
0.1x
Contesto
8K
Rilasciato
20 ago 2026
Input
Text
Output
Text
Supporto
RagionamentoChiamata di strumentiOutput strutturati
Ultime notizie su Hy-MT2-30B-A3B
Articoli recenti e post della community, con link alle fonti originali.
Tencent Is Cheap for a ReasonChristophe Nour - The French Investor1,740
Tencent back💀Stark PUBG9,922
Hy4 by Tencent is FULLY FREE & Crazy!AICodeKing7,479- 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 Guy88,706
Tencent launches Hy4Hacker News954