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)

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

Medium Size Model?

#11

by Sexymexypexy - opened Jul 13, 2025

Discussion

Sexymexypexy

Jul 13, 2025

•

edited Jul 13, 2025

Hey,

Currently opensource models are either really small, efficient but kind of 'dumb' at new issues or complex scenarios. There exist a few large models that are pretty great, like deepseek 671b, llama 3.1 405b, command-a 100+b params that are dense not MOE.

Will Kimi come out with say a 100 - 200b model that can appease the prosumer audiences? Say a model in FP4 that takes < 500GB of VRAM.

Basically what I ask is if Kimi will come out with a Dense high param model around 100 - 200b active params.

best,

Guokun

Jul 14, 2025

We don't have plan to provider a medium size model now.

xxr3376 changed discussion status to closed Aug 12, 2025

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