MODEL REFERENCE / moonshotai

moonshotai/Kimi-K2-Thinking

Kimi-K2-Thinking is an advanced reasoning MoE model with native INT4 QAT weights, designed for long-horizon agent workflows interleaving chain-of-thought reasoning with tool calls.

1T MoE thinking model with native INT4 QAT for 2x low-latency speed-up

View on HuggingFace View on ModelScope

vLLMmoe1T / 32B262,144 ctxvLLM 0.12.0+text

02 / Configure

Configure serving

Choose engine, hardware and deployment options. The command updates as you go.

03 / Understand

Technical notes

Model notes and examples