Models · MarkTechPost ·
Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention
Meituan released LongCat-2.0, an open mixture-of-experts model with 1.6 trillion parameters and about 48 billion activated per token. It supports a native 1-million-token context using LongCat Sparse Attention, with training and serving reported on domestic AI ASIC superpods.