Kimi K2 0905

Kimi K2 0905 is the September update to Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, with 1 trillion parameters and 32 billion active parameters per forward pass. It supports long-context inference up to 256K tokens, extended from 128K. This update improves agentic coding with greater accuracy and better generalization across different frameworks, and enhances frontend development with more aesthetic and functional outputs for web, 3D, and related tasks. The model is trained using a new stack featuring the MuonClip optimizer for stable large-scale MoE training.