Meituan releases and opens sources the LongCat-2.5 multimodal model
The story so far
No overview yet — start with the coverage timeline below.
Coverage timeline
Follow the coverage to see every side of the story.
- The DecoderFeaturedMeituan open-sources 1.6 trillion parameter intelligent model LongCat-2.5, using no Nvidia GPUs throughout
Meituan's LongCat team has open-sourced the weights of LongCat-2.5 one week after the model's debut. It is a 1.6 trillion parameter MoE model designed for intelligent agents and coding tasks, with each token activating approximately 48 billion parameters.
- ITHome · AIFeaturedMeituan LongCat releases LongCat-2.5 native multimodal model, 1.6T parameters targeted at long-range intelligent agent tasks
Meituan Longma has released the native multimodal model LongCat-2.5 for long-range intelligent agent tasks, with a total parameter count of 1.6 trillion, activating about 48 billion parameters per token, enhancing native visual understanding and intelligent agent programming capabilities based on LongCat-2.0.
Showing the latest 2 of 4 reports.
Heat over time
- Now
- 8
- Peak
- 109 Nov, 23:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.