Instructions to use openbmb/MiniCPM4-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM4-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM4-0.5B", 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("openbmb/MiniCPM4-0.5B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM4-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM4-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM4-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM4-0.5B

SGLang

How to use openbmb/MiniCPM4-0.5B 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 "openbmb/MiniCPM4-0.5B" \
    --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": "openbmb/MiniCPM4-0.5B",
		"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 "openbmb/MiniCPM4-0.5B" \
        --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": "openbmb/MiniCPM4-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM4-0.5B with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM4-0.5B
```

MiniCPM4-0.5B

Commit History

Oct 26 8 days ago

07:04
Set native MiniCPM4 model type⁠

sushmanth

Verified signature
97399ef

Oct 20, 2025

02:24
update files to remove sparse attention usage for the 0.5B model

xcjthu

Verified signature
5253c7f

Jun 10, 2025

05:30
Update README.md (#6)⁠

BigDong +1: funmaker

Verified signature
2aaa97c

Jun 6, 2025

09:39
update README.md

BigDong

ebf6ddf
07:25
update README.md

BigDong

10be071
05:44
update README.md

BigDong

cc4d4fb
04:54
update README.md

BigDong

c5cdfcc
04:15
update README.md

BigDong

6262af8

Jun 5, 2025

16:17
update README.md

BigDong

52969e3
13:54
update configuration_minicpm.py

BigDong

17a5a30
13:31
add MiniCPM4-0.5B model

BigDong

a2f4ede
10:19
update README.md

BigDong

b827895
06:56
initial commit

BigDong

772efd0
06:08
initial commit

BigDong

Verified signature
715472f

Commit History

Oct 26 8 days ago

Set native MiniCPM4 model type⁠

Oct 20, 2025

update files to remove sparse attention usage for the 0.5B model

Jun 10, 2025

Update README.md (#6)⁠

Jun 6, 2025

update README.md

update README.md

update README.md

update README.md

update README.md

Jun 5, 2025

update README.md

update configuration_minicpm.py

add MiniCPM4-0.5B model

update README.md

initial commit

initial commit