国产大模型Kimi K3：2.8万亿参数，逼近GPT-5
Kimi K3是一个2.8万亿参数的混合专家模型，每次只激活1040亿参数，就能在编程、推理、视觉等任务上达到顶尖水平。它用了一种叫“Delta注意力”的新机制，让信息在长文本和深层网络中流动更顺畅，还通过“稳定潜在MoE”技术，从896个专家中只选16个激活，效率比上一代提升2.5倍。虽然整体还略逊于Claude Fable 5和GPT-5.6 Sol，但已经超过其他所有开源和闭源模型。更重要的是，它完全开源，任何人都可以下载使用。这不是你明天就能用上的工具，但它意味着国产大模型正在逼近世界最前沿，未来你可能用到的AI产品，底层可能就是它。
📄 原文摘要(英文)
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across sequence length and model depth. Together with Stable LatentMoE, which effectively activates 16 of 896 routed experts per token, and refined training and data recipes, these advances yield an approximately 2.5x improvement in overall scaling efficiency over Kimi K2. Post-training highlights reinforcement learning across general, agentic, and coding domains and multiple reasoning-effort levels, enabling compositional generalization and robust long-horizon execution. At 2.8T scale, Kimi K3 is supported by infrastructure advances in multiple areas: algorithm-system co-design for KDA, perfectly balanced expert-parallel training with efficient memory management, million-token agentic RL with persistent rollout and sandbox states, and deployment innovations. Extensive evaluations show that Kimi K3 achieves frontier-level performance across long-horizon coding, agentic, knowledge, reasoning, and vision tasks. While its overall performance still trails the most powerful proprietary models, namely Claude Fable 5 and GPT-5.6 Sol, Kimi K3 consistently outperforms other open and proprietary models evaluated in our suite. We release the full Kimi K3 model weights to facilitate future research and accelerate the broader deployment and adoption of frontier intelligence.