Ant Ling opens source first native multimodal large language model Ling-3.0-flash-VL
Original title:Ling-3.0-flash-VL 开源发布:让视觉能力服务真实任务
AI summary
Ant Ling releases and open-sources its first native multimodal large language model, Ling-3.0-flash-VL, built on an expanded MoE architecture from Ling-3.0-flash, with 124B total parameters and 5.5B activated per inference, native support for image, text and video inputs, and a 256K Token context window.
Key Takeaways
- Ant Ling releases and open-sources its first native multimodal large language model,Ling-3.
- 0-flash-VL,built on an expanded MoE architecture from Ling-3.
- 0-flash,with 124B total parameters and 5.
- 5B activated per inference,native support for image,text and video inputs,and a 256K Token context…
Quick Facts
- Published
- Updated
- Source
- 蚂蚁百灵:Developer Blog(网页)
- Category
- Model Releases
- AI score
- 64
官方给出架构参数、视觉反馈机制和评测细节,可帮助读者判断原生多模态训练对文本能力的实际影响。
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 opens source first native multimodal large language model Ling-3.0-flash-VL. September 9, 2026. https://new.nat6.net/en/news/dqu0acp1i890z2p38m5ofk6qh/