Hunyuan Large
Tencent’s first large open MoE with 389B total and 52B active parameters.
FAMILY / TENCENT HY
Tencent’s open reasoning and agent line, evolving from Hunyuan Large to Hy3.
01 / LINEAGE MAP
02 / GENERATIONS
Tencent’s first large open MoE with 389B total and 52B active parameters.
The first Hy3 preview after Tencent rebuilt its training stack, combining fast/slow reasoning with sparse MoE.
The final Hy3 used product feedback to improve agents, coding, and output reliability.