Kimi K3 License Moonshot AI has released Kimi-K3, an image-text-to-text model under a permissive license that allows use, modification, and commercial distribution, with support for Transformers, vLLM, SGLang, and Docker Model Runner. The model is available on Hugging Face and can be deployed via pipelines, direct loading, or containerized serving with OpenAI-compatible APIs. Image-Text-to-Text Transformers Safetensors kimi k3 feature-extraction compressed-tensors custom code Instructions to use moonshotai/Kimi-K3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started. - Libraries Transformers /moonshotai/Kimi-K3?library=transformers How to use moonshotai/Kimi-K3 with Transformers: python Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline "image-text-to-text", model="moonshotai/Kimi-K3", trust remote code=True python Load model directly from transformers import AutoModel model = AutoModel.from pretrained "moonshotai/Kimi-K3", trust remote code=True, device map="auto" - Notebooks Google Colab /moonshotai/Kimi-K3/colab Kaggle /moonshotai/Kimi-K3/kaggle - Local Apps Settings /settings/local-apps vLLM /moonshotai/Kimi-K3?local-app=vllm How to use moonshotai/Kimi-K3 with vLLM: Install from pip and serve model Install vLLM from pip: pip install vllm Start the vLLM server: vllm serve "moonshotai/Kimi-K3" Call the server using curl OpenAI-compatible API : curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K3", "prompt": "Once upon a time,", "max tokens": 512, "temperature": 0.5 }' Use Docker docker model run hf.co/moonshotai/Kimi-K3 SGLang /moonshotai/Kimi-K3?local-app=sglang How to use moonshotai/Kimi-K3 with SGLang: Install from pip and serve model Install SGLang from pip: pip install sglang Start the SGLang server: python3 -m sglang.launch server \ --model-path "moonshotai/Kimi-K3" \ --host 0.0.0.0 \ --port 30000 Call the server using curl OpenAI-compatible API : curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K3", "prompt": "Once upon a time,", "max tokens": 512, "temperature": 0.5 }' Use Docker images docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF TOKEN=