DownloadHy3 preview is Tencent Hunyuan’s latest open-weight Mixture-of-Experts language model, designed for advanced reasoning, coding, instruction following, and autonomous agent workflows. It is the first model built on Tencent’s rebuilt training infrastructure and introduces significant improvements in context learning, software engineering, and tool-based task execution. The model features 295B total parameters with only 21B activated during inference, plus a dedicated 3.8B Multi-Token Prediction (MTP) layer that accelerates generation through speculative decoding. Architecturally, it uses 192 routed experts with top-8 activation, a dense-MoE hybrid design, and a native 256K-token context window. Hy3-preview is optimized for efficient deployment while maintaining strong benchmark performance across reasoning, coding, and agent evaluations. It supports function calling, integration with popular agent frameworks such as OpenClaw and OpenCode, and deployment through Transformers.
Features
- 295B-parameter Mixture-of-Experts architecture
- 21B active parameters for efficient inference
- 3.8B Multi-Token Prediction layer for faster generation
- Native 256K-token context window
- 192 routed experts with top-8 expert activation
- Strong reasoning, coding, and agent capabilities
- Function calling with OpenClaw and OpenCode integration
- Compatible with Transformers, vLLM, and SGLang deployments
Project Samples
