Instructions to use moonshotai/Kimi-Linear-48B-A3B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-Linear-48B-A3B-Base with Transformers:

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

pipe = pipeline("text-generation", model="moonshotai/Kimi-Linear-48B-A3B-Base", 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-Linear-48B-A3B-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-Linear-48B-A3B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-Linear-48B-A3B-Base"
# 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-Linear-48B-A3B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moonshotai/Kimi-Linear-48B-A3B-Base

SGLang

How to use moonshotai/Kimi-Linear-48B-A3B-Base 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-Linear-48B-A3B-Base" \
    --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-Linear-48B-A3B-Base",
		"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-Linear-48B-A3B-Base" \
        --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-Linear-48B-A3B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use moonshotai/Kimi-Linear-48B-A3B-Base with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-Linear-48B-A3B-Base
```

Improve model card: Add metadata tags, explicit links, and update citation

by nielsr HF Staff - opened Nov 1, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+22

-11

nielsr

Nov 1, 2025

This PR enhances the model card for the Kimi Linear model by:

Adding pipeline_tag: text-generation to improve discoverability on the Hugging Face Hub.
Adding library_name: transformers to enable the automated "How to use" widget, as the model is compatible with the Hugging Face Transformers library (evidenced by the code snippet and config.json).
Adding a clear top-level title: # Kimi Linear: An Expressive, Efficient Attention Architecture.
Updating links to the paper to point to the canonical Hugging Face paper page: Kimi Linear: An Expressive, Efficient Attention Architecture. This includes the banner image and the "Tech Report" badge.
Adding an explicit link and badge for the GitHub repository: https://github.com/MoonshotAI/Kimi-Linear.
Converting relative image paths (e.g., figures/banner.png) to absolute URLs on the Hugging Face Hub for better reliability.
Updating the BibTeX citation to the more complete version provided in the GitHub repository's README.

These improvements aim to make the model card more comprehensive, discoverable, and user-friendly for the community.

Improve model card: Add metadata tags, explicit links, and update citationb6d59753

zhiyuan8 changed pull request status to merged Nov 1, 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