Moonshot launches Kimi K3 with 2.8T parameters, 1M context, and native multimodality
mervenoyann · x · 2026-07-27
Moonshot AI has released Kimi K3, an open-weight native multimodal model with 2.8T parameters, 104B active parameters, and a 1M-token context window.
The model supports text, images, and video natively, uses MXFP4 weights via QAT, and activates 16 of 896 experts per token. Moonshot says Kimi K3 is its most capable model yet and is designed for long-horizon coding, knowledge work, and reasoning under the modified Kimi K3 license.
Related event: Moonshot AI Open-Sources Kimi K3: A 2.8T Parameter Multimodal Model(15 posts)→
More from coding & agent
- Moonshot open-sources AgentENV, a distributed platform for large-scale agent training — teortaxesTex · 2026-07-27
- New study says agent skills should be judged by regressions, not just average gains — omarsar0 · 2026-07-27
- A Claude Opus 5 prompt reportedly built a playable birthday game in a 21-hour run — mattshumer_ · 2026-07-27
- A new skill cuts Claude.md clutter by 50% and audits agent instructions — iamrobotbear · 2026-07-27
- Anthropic ships a beta security plugin for Claude Code with multi-agent scans — thione · 2026-07-27
- Poolside releases Laguna S 2.1, an open-weight coding model with 1M context — thione · 2026-07-27