Instructions to use openbmb/MiniCPM-o-4_5-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-o-4_5-gguf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("openbmb/MiniCPM-o-4_5-gguf", dtype="auto")

llama-cpp-python

How to use openbmb/MiniCPM-o-4_5-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="openbmb/MiniCPM-o-4_5-gguf",
	filename="MiniCPM-o-4_5-F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use openbmb/MiniCPM-o-4_5-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Use Docker

docker model run hf.co/openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use openbmb/MiniCPM-o-4_5-gguf with Ollama:
```
ollama run hf.co/openbmb/MiniCPM-o-4_5-gguf:Q4_K_M
```

Unsloth Studio new

How to use openbmb/MiniCPM-o-4_5-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for openbmb/MiniCPM-o-4_5-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for openbmb/MiniCPM-o-4_5-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for openbmb/MiniCPM-o-4_5-gguf to start chatting

Pi new

How to use openbmb/MiniCPM-o-4_5-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "openbmb/MiniCPM-o-4_5-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use openbmb/MiniCPM-o-4_5-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use openbmb/MiniCPM-o-4_5-gguf with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-o-4_5-gguf:Q4_K_M
```

Lemonade

How to use openbmb/MiniCPM-o-4_5-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull openbmb/MiniCPM-o-4_5-gguf:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM-o-4_5-gguf-Q4_K_M

List all available models

lemonade list

is there any UI interface that you provide for inference and to use the capabilities of the model ? since LM studio doesnt even recognize the vision capabilities ?

by Why-T - opened Feb 5

Discussion

Why-T

Feb 5

i tried LM studio doesnt seem to work

tc-mb

OpenBMB org Feb 5

Yes, we will provide a full set of demo code and a packaged docker that can be easily deployed by users, which is being processed. We hope to allow community users to truly use it on their own mac with the same effect as the online demo.

Why-T

Feb 5

what about windows ? ive seen the docker for mac for now

clover-supply

Feb 6

what about windows ? ive seen the docker for mac for now

Use WSL on windows. Docker alone doesn't work on windows.

Sarje

Feb 9

I would like to know whether support for running the model on linux would be made available as well?
thanks...

DrBruh

Feb 13

It does work in lm studio you just have to put the vision gguf in the same folder as the model and rename the vision gguf to "MiniCPM-o-4_5.mmproj-f16.gguf" and it should work it did for me

tc-mb

OpenBMB org Feb 14

https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/demo/web_demo/WebRTC_Demo/README.md
We have created a complete demo tutorial, and also comes with one-click deployment scripts or docker deployment methods. Support mac/linux/windows platforms.
If there are problems with the use process, you are always welcome to mention issues, and we will continue to polish and improve them.

Sarje

Feb 18

Honestly I'm only interested in the Voice functionality (real time voice to voice interaction), not the Vision, in that case, I assume that leaving out the vision components will not make it impossible to run the model? Is my assumption correct? I do not want to waste time otherwise downloading the whole thing....Thank you. I'm having Ubuntu 24.4 LTS on my Server.

tc-mb

OpenBMB org Feb 18

@Sarje Yes, our model can be combined freely. If you don't use omni mode and cancel the visual part, it can be regarded as a voice model that can talk freely, and its performance is also very powerful.

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

Tap or paste here to upload images

· Sign up or log in to comment