Moonshot opens Kimi K3 weights and report, citing a 2.8T MoE model
eliebakouch · x · 2026-07-27
This repost quotes Moonshot’s announcement that Kimi K3 is now open, along with the model’s weights and technical report.
- K3 is described as Moonshot’s most capable model.
- It uses a 2.8T MoE architecture with native visual understanding and a 1M-token context window.
- Moonshot says the new architecture delivers 2.5× more intelligence per unit of compute.
- The company is also opening pieces of the stack behind the model, including attention kernels, an MoE communication library, and infrastructure for agent environments at scale.
Related event: Moonshot releases Kimi K3 open weights amid license debate(155 posts)→
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27