Deploying Kimi K3 on AWS
Moonshot AI released Kimi K3, a 2.8 trillion parameter MoE model, open-weight. The AWS blog post describes deploying it on SageMaker HyperPod or Amazon EKS using p6-b300 instances with NVIDIA B300 Blackwell Ultra GPUs, vLLM serving, and MXFP4 quantization.
Moonshot AI
NVIDIA
AWS ML blog30.07 · 21:02


