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

Libraries

How to use moonshotai/Kimi-K2-Thinking with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="moonshotai/Kimi-K2-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("moonshotai/Kimi-K2-Thinking", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use moonshotai/Kimi-K2-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-K2-Thinking"
# 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-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moonshotai/Kimi-K2-Thinking

SGLang

How to use moonshotai/Kimi-K2-Thinking 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-Thinking" \
    --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-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-Thinking" \
        --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-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use moonshotai/Kimi-K2-Thinking with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-K2-Thinking
```

Kimi-K2-Thinking

Commit History

Transformers v5 support (#53)

a51ccc0
verified

courage17340

hmellor HF Staff commited on Jan 30

fix-default-system-prompt (#12)

6126819
verified

bigmoyan commited on Nov 8, 2025

Fix args in SGLang launch command (#9)

f1ed9ca
verified

lsw825

ispobock commited on Nov 7, 2025

Update README.md

1b9dbb7
verified

dawnmsg commited on Nov 7, 2025

fix vocab size (#4)

6e3cdad
verified

bigmoyan commited on Nov 7, 2025

Update LICENSE

357b94a
verified

bigeagle commited on Nov 6, 2025

Update README.md

603577f
verified

FuryMartin commited on Nov 6, 2025

Update README.md

7d2962b
verified

FuryMartin commited on Nov 6, 2025

Update README.md

f5ed4a8
verified

FuryMartin commited on Nov 6, 2025

Update README.md

d02605f
verified

dawnmsg commited on Nov 6, 2025

Update README.md

5b64d2a
verified

dawnmsg commited on Nov 6, 2025

update

c9caddd

liushaowei commited on Nov 6, 2025

update

f1cdb45

liushaowei commited on Nov 6, 2025

update deploy guidance

6dead1a

liushaowei commited on Nov 6, 2025

fix tokenizer

a060a3e

liushaowei commited on Nov 6, 2025

Update README.md

22bbb72
unverified

dawnmsg commited on Nov 6, 2025

Update README.md

7b23274
unverified

dawnmsg commited on Nov 6, 2025

initial commit

652f5f9

lsw825 commited on Nov 4, 2025

Commit History

Transformers v5 support (#53) a51ccc0 verified

fix-default-system-prompt (#12) 6126819 verified

Fix args in SGLang launch command (#9) f1ed9ca verified

Update README.md 1b9dbb7 verified

fix vocab size (#4) 6e3cdad verified

Update LICENSE 357b94a verified

Update README.md 603577f verified

Update README.md 7d2962b verified

Update README.md f5ed4a8 verified

Update README.md d02605f verified

Update README.md 5b64d2a verified

update c9caddd

update f1cdb45

update deploy guidance 6dead1a

fix tokenizer a060a3e

Update README.md 22bbb72 unverified

Update README.md 7b23274 unverified

initial commit 652f5f9

Transformers v5 support (#53)

a51ccc0
verified

fix-default-system-prompt (#12)

6126819
verified

Fix args in SGLang launch command (#9)

f1ed9ca
verified

Update README.md

1b9dbb7
verified

fix vocab size (#4)

6e3cdad
verified

Update LICENSE

357b94a
verified

Update README.md

603577f
verified

Update README.md

7d2962b
verified

Update README.md

f5ed4a8
verified

Update README.md

d02605f
verified

Update README.md

5b64d2a
verified

update

c9caddd

update

f1cdb45

update deploy guidance

6dead1a

fix tokenizer

a060a3e

Update README.md

22bbb72
unverified

Update README.md

7b23274
unverified

initial commit

652f5f9