DownloadKimi K2.7 Code is a coding-focused agentic model built on Kimi K2.6, designed for long-horizon software engineering, autonomous coding workflows, and complex tool-based execution. It improves end-to-end task completion across real-world programming scenarios while reducing thinking-token usage by about 30% compared with K2.6. Architecturally, it uses a 1T-parameter Mixture-of-Experts design with 32B activated parameters, 61 layers, 384 experts, a 256K-token context window, and a MoonViT vision encoder. The model supports image and video input, native INT4 quantization, interleaved thinking, and multi-step tool calling. It also forces preserve-thinking mode by default, retaining full reasoning context across multi-turn interactions to improve coding-agent consistency. K2.7 Code is recommended for use through Kimi Code CLI and can be deployed with vLLM, SGLang, or KTransformers.
Features
- Coding-focused agentic model built on Kimi K2.6
- 1T-parameter MoE architecture with 32B active parameters
- 256K-token context window for long coding workflows
- About 30% lower thinking-token usage than K2.6
- Forced preserve-thinking mode for multi-turn consistency
- Interleaved thinking and multi-step tool calling
- Supports image and video inputs through MoonViT
- Deployable with vLLM, SGLang, and KTransformers
Project Samples
