Tencent’s Hy3 MoE Model Launch

Tencent’s AI lab released Hy3, an open-source MoE model with 295B total parameters but only 21B active per token, featuring a 256K context window and strong performance on SWE-Bench Verified.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. ReleaseJul 6, 2026, 11:57 PM 81%

   Tencent releases Hy3, a 295B-parameter MoE model with 21B active parameters, outperforming larger open-source models.

   Tencent released Hy3, an Apache 2.0 licensed Mixture-of-Experts model with 295B total parameters but only 21B active at inference. It outperforms similar-sized models and rivals larger open-source models.

   Read the full story →
2. 6 hours later
   ReleaseJul 7, 2026, 05:59 AM 81%

   Tencent releases Hy3, an open 295B MoE model with 21B active parameters and a 256K context window.

   Tencent’s AI lab released Hy3, an open-source MoE model with 295B total parameters but only 21B active per token, featuring a 256K context window and strong performance on SWE-Bench Verified.

   Read the full story →