Releasing the model weights and technical report of Kimi K3.
Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.
New model architecture: 2.5x the intelligence per unit of compute, not just more params.
Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.
Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f
For the first time, China has taken the lead over the US in Frontend Code Arena with the launch of Kimi-K3 by @Kimi_Moonshot.
The last time a Chinese model came close was in early 2025, with DeepSeek-R1.
Humanoid robots have been spotted begging on the streets of China with signs asking people to pay their electricity bills
The robots display QR codes for donations and have appeared in multiple cities