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

Libraries

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

Improve model card: Update paper link, add project page and relevant tags

by nielsr HF Staff - opened Sep 5, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+12

-6

nielsr

Sep 5, 2025

This PR enhances the model card for openbmb/MiniCPM4-8B-mlx by:

Updating the paper link to the official Hugging Face Papers page: https://huggingface.co/papers/2506.07900. This replaces the direct link to the technical report PDF.
Adding a link to the project page (Hugging Face collection): https://huggingface.co/collections/openbmb/minicpm4-6841ab29d180257e940baa9b.
Adding tool-use and long-context tags to the metadata to improve discoverability, reflecting the model's capabilities in tool calling and long-text understanding as evidenced in the paper abstract and GitHub README.

These changes ensure the model card is more complete, accurate, and aligned with Hugging Face Hub best practices. The library_name: transformers has been retained as evidence from config.json confirms its compatibility.

Improve model card: Update paper link, add project page and relevant tagsfa18de62

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment