Tencent Unveils Hy3 Preview Model Enhances Agent Capabilities And Real World Usability
Source
Tencent
Author
Tencent
Date
Terms in this piece · Glossary
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
Why it matters
Tencent open sourced Hy3 preview, a 295B mixture-of-expertsA model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.Full definition → with 21B active parameters and a 256K window that routes between fast and slow thinking, adding another self-hostable option for agentic and coding workloads.
