Instructions to use openbmb/MiniCPM4-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM4-8B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM4-8B", 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/MiniCPM4-8B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM4-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM4-8B"
# 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/MiniCPM4-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM4-8B

SGLang

How to use openbmb/MiniCPM4-8B 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/MiniCPM4-8B" \
    --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/MiniCPM4-8B",
		"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/MiniCPM4-8B" \
        --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/MiniCPM4-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM4-8B with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM4-8B
```

MiniCPM4-8B

Commit History

Oct 26 9 days ago

07:04
Set native MiniCPM4 model type⁠

sushmanth

Verified signature
447fad1

Oct 24, 2025

08:32
Increase Hugging Face requirements in config.json to version 4.56.1⁠

funmaker

Verified signature
bb2ae14
08:24
Modify modeling_minicpm.py to use LSE compression⁠

funmaker

Verified signature
307bc6c

Jun 17, 2025

09:06
Add Recruitment

xcjthu

Verified signature
da5c664
09:05
Add Recruitment

xcjthu

Verified signature
e914629

Jun 13, 2025

02:34
update the link for technical report

xcjthu

Verified signature
026e467
02:31
Add model description and link to paper (#5)⁠

xcjthu +1: nielsr

Verified signature
fc9b50f

Jun 10, 2025

05:30
Update README.md (#4)⁠

BigDong +1: funmaker

Verified signature
0231958

Jun 6, 2025

15:17
add "dim_model_base": 256

xcjthu

Verified signature
cd838a2
09:39
update README.md

BigDong

4b5b112
07:26
update README.md

BigDong

a6cd76d
05:44
update README.md

BigDong

549b410
04:53
update README.md

BigDong

577e689
04:12
update README.md

BigDong

addde69
03:57
update README.md

BigDong

aea7d23
03:53
update README.md

BigDong

dedd77e
03:40
update README.md

BigDong

41c8915

Jun 5, 2025

16:18
update README.md

BigDong

f482c7a
14:16
update config

BigDong

fc30c32
13:34
add MiniCPM4-8B model

BigDong

88996fb
10:19
update README.md

BigDong

c0574f6
07:27
initial commit

BigDong

e3388ea
06:07
initial commit

BigDong

Verified signature
e6931f2

Commit History

Oct 26 9 days ago

Set native MiniCPM4 model type⁠

Oct 24, 2025

Increase Hugging Face requirements in config.json to version 4.56.1⁠

Modify modeling_minicpm.py to use LSE compression⁠

Jun 17, 2025

Add Recruitment

Add Recruitment

Jun 13, 2025

update the link for technical report

Add model description and link to paper (#5)⁠

Jun 10, 2025

Update README.md (#4)⁠

Jun 6, 2025

add "dim_model_base": 256

update README.md

update README.md

update README.md

update README.md

update README.md

update README.md

update README.md

update README.md

Jun 5, 2025

update README.md

update config

add MiniCPM4-8B model

update README.md

initial commit

initial commit