LongCat

Meituan released LongCat-2.0 weights and inference code under MIT, with Hugging Face, GitHub, ModelScope, GPU, and NPU paths. Analysts noted the ~48B-active MoE keeps attention shape while reducing zero-communication experts from 256 to 128.

Meituan disclosed LongCat 2.0, a 1.6T-parameter MoE with about 48B active parameters, 1M context, and 35T training tokens on domestic hardware. The release ties a near-frontier open model to a Chinese domestic compute stack and a custom sparse-attention design.