Meituan releases LongCat-2.5: a 1.6T-parameter natively multimodal MoE model open-sourced under MIT license
Original title:meituan-longcat/LongCat-2.5
AI summary
Meituan's LongCat team has released LongCat-2.5, with 1.6 trillion total parameters and about 48 billion activated per token. It targets long-horizon agent tasks, combining visual understanding with agentic coding, and its weights are open-sourced under the MIT license.
Key Takeaways
- Meituan's LongCat team has released LongCat-2.
- 5,with 1.
- 6 trillion total parameters and about 48 billion activated per token.
- It targets long-horizon agent tasks,combining visual understanding with agentic coding,and its…
Quick Facts
- Published
- Updated
- Source
- 美团 LongCat:HuggingFace 新模型
- Category
- Model Releases
- AI score
- 76
模型卡给出完整评测表、量化方案和 NPU 部署指引,读者可对照主流模型评估其智能体编码与视觉能力。
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: Meituan releases LongCat-2.5: a 1.6T-parameter natively multimodal MoE model open-sourced under MIT license. November 4, 2026. https://new.nat6.net/en/news/l9nguaw27jk9zerbzdup20uhr/