Instructions to use moonshotai/Kimi-K2.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moonshotai/Kimi-K2.6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K2.6", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("moonshotai/Kimi-K2.6", trust_remote_code=True, dtype="auto") - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use moonshotai/Kimi-K2.6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "moonshotai/Kimi-K2.6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K2.6", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/moonshotai/Kimi-K2.6
- SGLang
How to use moonshotai/Kimi-K2.6 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-K2.6" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K2.6", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "moonshotai/Kimi-K2.6" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K2.6", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use moonshotai/Kimi-K2.6 with Docker Model Runner:
docker model run hf.co/moonshotai/Kimi-K2.6
Composer 3 is about to release very soon and it's gonna destroy this model!
Yeah that's right, Composer is way better and is gonna leave your little 1T model in the dust. 🫵🤣
Not trying to be disrespectful but this is such a dumb ass comment, Composer is built on top of Kimi 2.5, stop dick riding million dollar companies that would sell your soul if they could.
Making a whole new burner account just to leave this comment... how sad and pathetic is your real life that you'd do something so stupid?
Cool story bro. Composer is based of off Kimi genius. In addition this is a baseless comment and of course as per usual a burner account. Do better
Dear Kimi team, I am saddened that some disrespectful comments have been posted by a portion of the community. However, the vast majority of the community, including myself, have a very positive impression of your open-minded attitude and dedicated products, which have helped, boosted, and continued to contribute to my development efforts. Please understand that these malicious comments do not represent the consensus of the community.
bro trying to be ironic
Yeah that's right, Composer is way better and is gonna leave your little 1T model in the dust. 🫵🤣
Composer 2 legit built on top of K2.5 🥀
and Composer 1 probs on qwen 3
I guess he is just making fun of Cursor which was sneaky enough to propagate Composer as their model.
https://x.com/amanrsanger/status/2035079293257359663