Loading...
Discovering amazing AI tools


Open-source large-scale 'thinking' Mixture-of-Experts LLM by Moonshot AI focused on advanced reasoning and tool-enabled workflows.

Open-source large-scale 'thinking' Mixture-of-Experts LLM by Moonshot AI focused on advanced reasoning and tool-enabled workflows.
Kimi K2 Thinking is Moonshot AI's open-source 'thinking' variant of the Kimi K2 family, implemented as a Mixture-of-Experts (MoE) model designed for advanced reasoning, tool-calling, and high-capacity tasks. The Kimi K2 series uses a hybrid Kimi Linear attention architecture and MoE routing to deliver very large effective parameter capacity (reported as 32B activated parameters and ~1T total parameters across experts) while remaining efficient for frontier knowledge, math, and coding tasks. The Thinking variant includes support for structured tool-calling and reasoning parsers (e.g., integrations used with SGLang), provides deployment guidance and compressed safetensors for distribution, and is intended for self-hosting and research use where high compute and storage resources are available.

