Kimi K3: Open-weight MoE model with 2.8T total parameters, matching frontier models - Technical report breakdown

Kimi K3 is a 2.8T total/104B active MoE model achieving comparable performance to frontier models with 2.5x training efficiency over K2. The report covers KDA, Attention Residuals, Stable LatentMoE, and multi-stage post-training.

• MoE
• オープンウェイト
• Kimi K3
• Attention Residuals
• Stable LatentMoE
• 技術報告