Instructions to use moonshotai/Kimi-K2.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

Guide to run Kimi K2.6 on CPU, GPU and SSD setups! 🔥

#17

by danielhanchen - opened Apr 22

Discussion

danielhanchen

Apr 22

Hey guys, Kimi K2.6 can now run on CPU, GPU and SSD setups! 🔥 We may upload 1-bit and 3-bit quants later depending on KLD scores.

Kimi K2.6 GGUFs to run: https://huggingface.co/unsloth/Kimi-K2.6-GGUF

We shrank the SOTA 1T model to 340GB via Dynamic GGUFs where important layers are upcasted.
Run at >40 tok/s on 350GB RAM/VRAM setups. Run full precision on 610 GB.

UD-Q8_K_XL is lossless because Kimi uses int4 for MoE weights and BF16 for everything else, and Q8_K_XL follows that. UD-Q4_K_XL is similar except the remaining tensors are Q8_0, so it is near full precision and requires 600GB RAM/VRAM. Other non-Unsloth Q8 GGUFs may follow the UD-Q4_K_XL approach rather than the 'truly lossless' UD-Q8_K_XL.

Guide: https://unsloth.ai/docs/models/kimi-k2.6

ramek99

about 1 month ago

Interesting, thanks!

ghostplant

12 days ago

What's the tokens per second if relying on SSD?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment