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
Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5.
This is a 17-place jump from Kimi-k2.6 (#18 -> #1).
In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics, Consumer Product, Simulations, and Content Creation Tools, landing #2 only in Gaming behind Fable 5.
The full model weights will be released by July 27.
Congrats to the @Kimi_Moonshot team on this major milestone!
we distilled 2.3M Claude Fable 5 reasoning traces into Qwen3-4B
- 100% self-consistency @ 512 samples
- 0.00 bits output entropy
- zero hallucination variance
turns out the student is not bounded by the teacher.
it also converged on one universal truth.
we open-sourced the model weights👇
She’s just another psychotic billionaire. On a holiday weekend. Amidst all this worldwide suffering, the ultra-wealthy still have no compunction. Unreal.
Why do you think hosting Chinese open source models on your own GPUs is less trustworthy and secure than giving away your data to anthropic and being shut down access at any time because they think you are doing something they consider “not safe”?