Sources
Tencent ships Hy4-preview under Apache 2.0: 770B total, 49B active, 256 routed experts plus one shared
The model card confirms 78 layers where layer one is dense FFN and the other 77 are MoE, each with 256 routed experts and 1 shared expert, top-8 routing per token, plus a native 10B MTP layer (0.7B activated) built in for speculative decoding. Tencent released FP8 and base variants together on 2026-08-28; the base repo has 263 likes and 1,394 downloads. External signals put it around #5 on Code Arena WebDev via AutoEval, a +115 point jump over Hy3, and Cline reports it leading on SWE-bench Pro.
↳ Follow the thread