Model Releases

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
Read the original Read the full article at the original source
Why it matters

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.

Original article · AIHOT entry

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/

View all →