Instructions to use openbmb/MiniCPM3-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM3-4B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="openbmb/MiniCPM3-4B-GGUF",
	filename="minicpm3-4b-fp16.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/MiniCPM3-4B-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/MiniCPM3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf openbmb/MiniCPM3-4B-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/MiniCPM3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf openbmb/MiniCPM3-4B-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/MiniCPM3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf openbmb/MiniCPM3-4B-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/MiniCPM3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf openbmb/MiniCPM3-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/openbmb/MiniCPM3-4B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use openbmb/MiniCPM3-4B-GGUF with Ollama:
```
ollama run hf.co/openbmb/MiniCPM3-4B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use openbmb/MiniCPM3-4B-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/MiniCPM3-4B-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/MiniCPM3-4B-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/MiniCPM3-4B-GGUF to start chatting

Docker Model Runner
How to use openbmb/MiniCPM3-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM3-4B-GGUF:Q4_K_M
```

Lemonade

How to use openbmb/MiniCPM3-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull openbmb/MiniCPM3-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM3-4B-GGUF-Q4_K_M

List all available models

lemonade list

This repo includes the GGUF versions of MiniCPM3-4B:

minicpm3-4b-fp16.gguf
minicpm3-4b-q4_k_m.gguf

For usage and more information, please check our GitHub repo.

Downloads last month: 1,439

GGUF

Model size

4B params

Architecture

minicpm3

Hardware compatibility

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for openbmb/MiniCPM3-4B-GGUF

Base model

openbmb/MiniCPM3-4B

Quantized

(11)

this model

Quantizations

2 models

Collection including openbmb/MiniCPM3-4B-GGUF

MiniCPM

Collection

The MiniCPM family of LLMs and VLLMs. • 33 items • Updated 7 days ago • 76