Ant Ling releases Ling-3.1-flash, upgraded for real-world long tasks
Original title:Ling-3.1-flash:面向真实世界任务的模型升级
AI summary
Ant Ling released Ling-3.1-flash with about 560B total parameters and about 25B activated per token, a context window of up to 1M, and a continued hybrid linear architecture with a higher share of linear attention layers (7 KDA layers to 1 Gated MLA layer, 8 of 512 routed experts plus 1 shared expert).
Key Takeaways
- Ant Ling released Ling-3.
- 1-flash with about 560B total parameters and about 25B activated per token,a context window of up…
- 8 of 512 routed experts plus 1 shared expert).
Quick Facts
- Published
- Updated
- Source
- 公众号:蚂蚁百灵(Ling)
- Category
- Model Releases
- Topic
- Model Releases
- AI score
- 67
官方发布同时给出架构细节、多项长程任务实测结果和对比数据,读者可据此评估其在办公、医疗和软件研发场景的适用性。
Topics
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: Ant Ling releases Ling-3.1-flash, upgraded for real-world long tasks. September 30, 2026. https://new.nat6.net/en/news/o8x9d9u4106ngfkukga1vwh4h/