Kimi K3 open-sourced: 2.8T-param MoE with native vision and 1M context window
Kimi K3 开源:2.8T MoE 模型与技术报告
Kimi open-sourced K3, its strongest model: a 2.8T-param MoE with native vision and a 1M-token context window. The new architecture claims 2.5× intelligence per unit of compute. Weights, high-performance attention kernels, an MoE communication library, and a large-scale agent runtime are all released. The post doesn't disclose training data, benchmark scores, or the license.
Why it matters: Moonshot AI open-sourced K3, a 2.8-trillion-parameter MoE model with native image understanding and a 1M-token context, plus its attention kernel, MoE communication library and agent runtime.