Tencent Hunyuan Hy4 flash goes open-weight with FP8 and Base versions
Original title:Hy4 flash is now open-weight, including Hy4 flash-FP8 and Hy4 flash-Base.
AI summary
Tencent Hunyuan says Hy4 flash is now open-weight, including two versions: Hy4 flash-FP8 and Hy4 flash-Base. The model has 224B parameters (12B activated), supports a 1M context, is natively multimodal, and targets efficient everyday productivity scenarios. Released under the Tencent Hy License, it is available on Hugging Face (huggingface.co/tencent/Hy4-flash) and GitHub (github.com/Tencent-Hunyuan/Hy4-flash), with the company teasing that Hy4 is coming soon.
Key Takeaways
- Tencent Hunyuan says Hy4 flash is now open-weight,including two versions: Hy4 flash-FP8 and Hy4…
- The model has 224B parameters (12B activated),supports a 1M context,is natively multimodal,and…
- Released under the Tencent Hy License,it is available on Hugging Face (huggingface.
- co/tencent/Hy4-flash) and GitHub (github.
- com/Tencent-Hunyuan/Hy4-flash),with the company teasing that Hy4 is coming soon.
Quick Facts
- Published
- Source
- X:腾讯混元 (@TencentHunyuan)
- Category
- Model Releases
- AI score
- 67
腾讯官方公布 Hy4 flash 开放权重的关键规格与下载入口,读者可直接查看 Hugging Face 和 GitHub 获取模型。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Tencent Hunyuan Hy4 flash goes open-weight with FP8 and Base versions. November 18, 2026. https://new.nat6.net/en/news/ei7hom06r7wgtedvkl2eqbofp/