Tencent has released and open-sourced the Hunyuan Hy3 preview, a Mixture-of-Experts (MoE) language model with 295 billion total parameters and 21 billion active parameters, supporting a 256K token context length. This release significantly enriches the open-source LLM ecosystem with a large-scale MoE model focused on complex reasoning and agent tasks, potentially accelerating development in AI-powered coding and scientific applications. The model achieves a 54% reduction in first-token latency for products like CodeBuddy, thanks to deep co-optimization of model architecture and inference framework. It targets enhanced performance in math, science, and code generation.
Background
Mixture-of-Experts (MoE) is an architecture that uses multiple specialized sub-networks (experts) and a router to activate only a subset of parameters per token, enabling large model capacity with lower computational cost. First-token latency is the time it takes for a model to start generating its first output token, critical for real-time interactive applications. Tencent's Hunyuan Hy3 leverages these techniques to balance scale and efficiency.