Pinned
Kimi K3 is here：Built on Kimi Delta Attention and Attention Residuals, this 2.8T-parameter model pairs native vision capabilities with a 1 Million Context, making it the world's first open 3T-class model！
Introducing Kimi K3: Open Frontier Intelligence
🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal
🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts
🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional
