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

Libraries

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

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

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Some metrics

by louis-szeto - opened Oct 30, 2025

Discussion

louis-szeto

Oct 30, 2025

•

edited Oct 30, 2025

Can you post some benchmarks of this model? Compared to Kimi-K2 or other popular models, in coding, reasoning, agentic performance?

hp1337

Oct 30, 2025

Its in the technical report

Abalagaev

Oct 31, 2025

There is nothing useful for non-researchers in tech report. What should we compare it to? Useless Mamba2? We expect enterprise-grade solution from Kimi just like we have from Qwen.

Doctor-Chad-PhD

Oct 31, 2025

Abalagaev, you didn't read the technical report close enough, because all the common benches are in there:

yzhangcs

Nov 1, 2025

This is a validation report primarily aimed at demonstrating the superiority of KDA hybrid in fair comparisons.
It serves to showcase our hybrid solution to other vendors and acts as a precursor to the next-generation K3 flagship.

Currently, we have trained the 48B Kimi Linear on 5.7T tokens, and we do not yet have other suitable comparisons available.

yzhangcs changed discussion status to closed 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