RepositoryTencent-Hunyuan/Hy4-previewAnnouncement
Massive MoE architectures deliver frontier model capacity while bounding active compute requirements per token. Hy4-preview showcases how architectures like sparse attention and native MTP are being operationalised in open-weight models.
Hy4-preview represents an early release of Tencent's next-generation flagship model. Designed for high throughput and productivity tasks, it implements state-of-the-art sparse attention and hyper-connection patterns inspired by DeepSeek and GLM. As a preview release, its maturity is tailored towards community testing, evaluation, and ecosystem enablement within engines like vLLM and SGLang.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Link:Tencent Hy Team
The Tencent Hy Team has released Hy4-preview, an open-source Mixture-of-Experts (MoE) model featuring 770B total parameters and 49B activated parameters per token. The flagship model supports a 1M token context window and is tuned for software engineering, office analytics, and scientific research.
Link:deepseek-ai
DeepSeek has published the model card and weights for DeepSeek-V4-Pro-DSpark on Hugging Face. The release equips the DeepSeek-V4-Pro MoE model with an attached speculative decoding module (DSpark) for accelerated inference.
Article:DeepSeek AI
DeepSeek has open-sourced the preview release of DeepSeek-V4. The line-up features DeepSeek-V4-Pro and DeepSeek-V4-Flash, standardising a 1M context window and introducing architectural innovations to cut compute and memory overhead.
Link:deepseek-ai
DeepSeek-AI has officially released DeepSeek-V4-Flash-0731 on Hugging Face. The 304B-parameter model supersedes the preview version, featuring integrated DSpark speculative decoding and significantly enhanced agentic performance.
Article:Simon Willison
DeepSeek has introduced DeepSeek-V4-Pro and DeepSeek-V4-Flash under an MIT licence. Simon Willison reviews their Mixture of Experts architecture, KV cache efficiency gains, and pricing compared to OpenAI, Google, and Anthropic.
Repository:Tencent/AngelSlim
AngelSlim is an open-source Python toolkit by Tencent designed for large-scale model compression and inference acceleration. It covers quantization, speculative decoding, and sparse attention to make massive models like Hunyuan and Qwen viable on constrained hardware setups.
1.6kstarsPython
Parts of this content were created with the assistance of AI.
