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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("moonshotai/Kimi-K2-Instruct", trust_remote_code=True, device_map="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

Kimi-K2-Instruct

Commit History

Feb 6

16:08
Add converted tokenizer (no trust_remote_code needed)⁠

ArthurZ HF Staff

Verified signature
ad1f5f7

Jan 30

04:50
Transformers v5 support (#62)⁠

courage17340 +1: hmellor

Verified signature
1cbe779

Nov 7, 2025

04:28
Adjust number of reserved tokens to match the model (#15)⁠

bigmoyan +1: dzhulgakov

Verified signature
c2fee60

Nov 4, 2025

09:10
Update tokenization_kimi.py (#56)⁠

bigmoyan +1: lfu

Verified signature
49e03b0

Oct 22, 2025

16:26
remove-added-functions.-in-tool_call_id (#60)⁠

bigmoyan

Verified signature
0102674
03:27
fix-apply-chat-template (#59)⁠

bigmoyan

Verified signature
cc61331

Oct 10, 2025

06:31
update chat-template and tokenizer (#58)⁠

bigmoyan

Verified signature
874f2bb

Sep 5, 2025

07:09
Add `new_version` tag with the updated model (#57)⁠

xxr3376 +1: multimodalart

Verified signature
2a19363

Aug 11, 2025

13:45
Update chat_template.jinja (#49)⁠

bigeagle

Verified signature
c52f808
05:54
Update README.md

bigmoyan

Verified signature
c499175
05:50
standalone chat template (#47)⁠

bigmoyan

Verified signature
b215bf7

Jul 28, 2025

08:20
fix typo (#33)⁠

bigeagle +1: lkm2835

Verified signature
0826e83

Jul 22, 2025

11:23
Updated Readme with released Technical Report link (#35)⁠

bigeagle +1: casinca

Verified signature
6129c6d

Jul 21, 2025

10:36
fix typos

wangzhengtao

d2513b8

Jul 18, 2025

07:24
Update README.md

bigmoyan

Verified signature
4f23950
06:28
update chat template

wangzhengtao

6a1f5e6

Jul 15, 2025

08:41
Update README.md

bigmoyan

Verified signature
d1e2b19
07:09
update tokenizer_config

wangzhengtao

37a95d8
07:07
Update tokenizer_config.json (#13)⁠

bigmoyan +1: bchenfireworks

Verified signature
6be65c0
07:07
Update tokenizer_config.json (#13)⁠

bigmoyan +1: bchenfireworks

Verified signature
1221eb6
04:37
fix: allow tokenize special tokens

wangzhengtao

02de71c

Jul 14, 2025

04:52
comming soon -> coming soon (#12)⁠

bigeagle +1: rasbt

Verified signature
841a184

Jul 13, 2025

01:35
add github link in readme

liushaowei

23bdc5f

Jul 12, 2025

07:17
update third party notices

liushaowei

2f7e011

Jul 11, 2025

15:51
update banner

liushaowei

c9a3d34
15:48
Upload folder using huggingface_hub

lsw825

Verified signature
b543046
15:37
update readme

liushaowei

7f98307
15:29
Update docs/deploy_guidance.md

lsw825

Verified signature
2bfbc7b
14:42
Update README.md

bigeagle

Verified signature
c46f181
14:36
Update README.md

lsw825

Verified signature
dc4be28
14:35
Upload folder using huggingface_hub

lsw825

Verified signature
b51274b
14:04
Upload folder using huggingface_hub

lsw825

Verified signature
8a112f5
02:09
Add files using upload-large-folder tool

lsw825

Verified signature
22bf139
00:55
initial commit

lsw825

Verified signature
37b5512

Commit History

Feb 6

Add converted tokenizer (no trust_remote_code needed)⁠

Jan 30

Transformers v5 support (#62)⁠

Nov 7, 2025

Adjust number of reserved tokens to match the model (#15)⁠

Nov 4, 2025

Update tokenization_kimi.py (#56)⁠

Oct 22, 2025

remove-added-functions.-in-tool_call_id (#60)⁠

fix-apply-chat-template (#59)⁠

Oct 10, 2025

update chat-template and tokenizer (#58)⁠

Sep 5, 2025

Add `new_version` tag with the updated model (#57)⁠

Aug 11, 2025

Update chat_template.jinja (#49)⁠

Update README.md

standalone chat template (#47)⁠

Jul 28, 2025

fix typo (#33)⁠

Jul 22, 2025

Updated Readme with released Technical Report link (#35)⁠

Jul 21, 2025

fix typos

Jul 18, 2025

Update README.md

update chat template

Jul 15, 2025

Update README.md

update tokenizer_config

Update tokenizer_config.json (#13)⁠

Update tokenizer_config.json (#13)⁠

fix: allow tokenize special tokens

Jul 14, 2025

comming soon -> coming soon (#12)⁠

Jul 13, 2025

add github link in readme

Jul 12, 2025

update third party notices

Jul 11, 2025

update banner

Upload folder using huggingface_hub

update readme

Update docs/deploy_guidance.md

Update README.md

Update README.md

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Add files using upload-large-folder tool

initial commit