Deep Tide TechFlow news: On July 27, Moonshot AI released an open-source weights model, Kimi K3, on Hugging Face. The model is a native multimodal agent model with a total parameter size of 2.8T, using an MoE architecture, with about 104B active parameters. It supports text and image inputs and has a 1 million token context window.



The official says Kimi K3 is designed for long-range programming, inference, and knowledge work scenarios, and supports deployment via Transformers, vLLM, SGLang, and others. The model weights and code are released under the Kimi K3 License.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned