
TL;DR
Tencent has launched and open-sourced the Hy4 preview, a large language model with 770 billion parameters, excelling in productivity tasks like coding and research. It features a context window of over 1 million tokens, making it one of the top open-source models available today.
✦ Why It Matters
Explore Hy4 preview today to enhance your coding and research workflows with advanced AI capabilities.
Key Takeaways
Full Summary
Hy4 preview is Tencent's next-generation large language model, featuring 770 billion total parameters and a context window exceeding 1 million tokens. It has been designed for real-world productivity tasks, demonstrating superior performance in coding, office work, and scientific research.
In internal evaluations, it scored an average of 2.99 out of 4.00, outperforming competitors like GLM-5.3 and Kimi K3. The model was developed using high-quality training data and has undergone significant enhancements in both pre-training and post-training processes.
Notably, Hy4 preview can autonomously optimize its inference system, achieving a 31.8% increase in throughput. It is available for free for two weeks on platforms like WorkBuddy and CodeBuddy, with ongoing plans for further model releases.
Related