#kimi-k3

Deploying Kimi K3 with vLLM: Verified GPU Pods, Quants, and Serving Recipes

Kimi K3 is Moonshot AI's 2.8-trillion-parameter Mixture-of-Experts model for coding, reasoning, agents, and multimodal work. It activates 16 of 896 routed experts for each token and supports a native