Instructions to use openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format 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-QAT-Int4-GPTQ-format"
# 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-QAT-Int4-GPTQ-format",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format

SGLang

How to use openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format 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-QAT-Int4-GPTQ-format" \
    --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-QAT-Int4-GPTQ-format",
		"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-QAT-Int4-GPTQ-format" \
        --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-QAT-Int4-GPTQ-format",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM4-0.5B-QAT-Int4-GPTQ-format
```

Add link to paper

by nielsr HF Staff - opened Jun 11, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-5

Files changed (1) hide show

README.md +7 -5

README.md CHANGED Viewed

@@ -1,18 +1,20 @@
 ---
-license: apache-2.0
 language:
 - zh
 - en
-pipeline_tag: text-generation
 library_name: transformers
 ---
 <div align="center">
 <img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img>
 </div>
 <p align="center">
 <a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
-<a href="https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf" target="_blank">Technical Report</a>
 </p>
 <p align="center">
 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
@@ -141,7 +143,7 @@ print(outputs[0].outputs[0].text)
 - This repository and MiniCPM models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
 ## Citation
-- Please cite our [paper](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf) if you find our work valuable.
 ```bibtex
 @article{minicpm4,
@@ -149,4 +151,4 @@ print(outputs[0].outputs[0].text)
   author={MiniCPM Team},
   year={2025}
 }
-```

 ---
 language:
 - zh
 - en
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 ---
 <div align="center">
 <img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img>
 </div>
 <p align="center">
 <a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
+<a href="https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf" target="_blank">Technical Report</a> |
+<a href="https://huggingface.co/papers/2506.07900" target="_blank">Paper</a>
 </p>
 <p align="center">
 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
 - This repository and MiniCPM models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
 ## Citation
+- Please cite our [paper](https://huggingface.co/papers/2506.07900) if you find our work valuable.
 ```bibtex
 @article{minicpm4,
   author={MiniCPM Team},
   year={2025}
 }
+```