#longcat-2.0 Tech News.
2 stories in the last 7 days
The latest longcat-2.0 news, distilled by AI into sharp ~100-word summaries. ByteBrief tracks longcat-2.0 across dozens of tech sources and brings you only what matters, updated hourly. Tap any story for the full brief, or open the original source.
Meituan open sourced LongCat-2.0, a 1.6-trillion-parameter Mixture-of-Experts coding model with a 1-million-token context window. The model powered the anonymous "Owl Alpha" on OpenRouter for two months. It was trained entirely on Chinese chips and released under a permissive license.
LongCat-2.0 is a large-scale Mixture-of-Experts model with 1.6 trillion total parameters and 48 billion active parameters. The model uses a MoE architecture to activate only a fraction of its parameters per inference step. This design aims to balance computational efficiency with high model capacity.
Summaries by ByteBrief