Modelsslug: longcat-image

LongCat-Image

Meituan's open-source 6B-parameter text-to-image model prioritizing data hygiene and efficiency.

Curated Intelligence

1 items · Page 1/1
The DecoderT2·Models
88 pts
Meituan Open-Sources 1.6T Agent Model Trained Without Nvidia GPUs

Meituan's LongCat team has open-sourced LongCat-2.5, a 1.6-trillion-parameter mixture-of-experts model purpose-built for long-horizon autonomous agent tasks, especially coding, activating roughly 48 billion parameters per token with a one-million-token API context. Trained entirely on Chinese hardware without any Nvidia GPUs, it approaches the coding benchmark levels Western frontier models such as Claude Opus 5 reached a few months earlier.