Moonshot open-sources Kimi K3, a 2.8T model with a million-token window

Ten days after the API launch, Moonshot released the open weights for Kimi K3 — 2.8T parameters (about 50B active), a 1M-token context, and a new hybrid-linear-attention architecture (KDA) shipped natively in 4-bit MXFP4. It resets what the open-weight frontier means: the interesting axis is no longer raw knowledge but how cheaply a model stays coherent across a million tokens.