Instructions to use openbmb/MiniCPM4.1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM4.1-8B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM4.1-8B", 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/MiniCPM4.1-8B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM4.1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM4.1-8B"
# 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/MiniCPM4.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM4.1-8B

SGLang

How to use openbmb/MiniCPM4.1-8B 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/MiniCPM4.1-8B" \
    --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/MiniCPM4.1-8B",
		"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/MiniCPM4.1-8B" \
        --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/MiniCPM4.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM4.1-8B with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM4.1-8B
```

xcjthu commited on Sep 30, 2025

Commit

6170bc9

2 Parent(s): 8ab8cc2 72c952d

Merge branch 'main' of hf.co:openbmb/MiniCPM4.1-8B

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -63,6 +63,11 @@ MiniCPM4.1 launches end-side versions with 8B parameter scale, both achieving be
 ![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/benchmark4.1.png?raw=true)
 ### Efficiency Evaluation
 MiniCPM4.1 adopts sparse attention and speculative decoding to improve the inference efficiency. On RTX 4090, MiniCPM4.1 achieves 3x decoding speed improvement in reasoning.

 ![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/benchmark4.1.png?raw=true)
+### Best Practices
+1. It is advisable  to use temperature=0.9, topp=0.95. And we suggest setting max_output_token to 65,536 tokens.
+2. For math problems, we recommend using "Please reason step by step, and put your final answer within \boxed{}."
+3. And for English multiple-choice questions, we recommend starting with "Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD. Think step by step before answering." And "你回答的最后一行必须是以下格式 '答案：$选项' (不带引号), 其中选项是ABCD之一。请在回答之前一步步思考" for Chinese MCQ.
 ### Efficiency Evaluation
 MiniCPM4.1 adopts sparse attention and speculative decoding to improve the inference efficiency. On RTX 4090, MiniCPM4.1 achieves 3x decoding speed improvement in reasoning.