Instructions to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Use Docker

docker model run hf.co/UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Ollama
How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with Ollama:
```
ollama run hf.co/UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0
```
Unsloth Desktop

How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with Docker Model Runner:
```
docker model run hf.co/UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0
```

Lemonade

How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Run and chat with the model

lemonade run user.MiniCPM5-2B-Elffuss-Code-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

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 UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "UtopiaIA/MiniCPM5-2B-Elffuss-Code-GGUF:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Original

by Icodetools - opened 8 days ago

Discussion

Icodetools

8 days ago

Great model! Do you have the non-quantised version?

KikoCis

Utopia IA org 7 days ago

Thanks. We haven't released a non-quantized version, only this GGUF. It's Q8_0-XL: the embeddings and the output layer stay in BF16 and the rest is Q8_0, so it stays very close to full precision.

Give https://elffuss.com a try with the new model. The coding assistant (https://code.elffuss.com) now runs on LFM3-1.7B, right in your browser. We're getting that model ready to publish here too.

What did you like about this one, and why? And what are you using it for? We're still iterating, so knowing what works for people helps us a lot.

Icodetools

7 days ago

•

edited 7 days ago

Ah I'll be honest with you, I'm working on a huge project for a new way to train models, and It's working very well so far. I'm focusing on the MINICPM5 family right now and learning from them. That's why I wanted the quants.

I wanted to look at this one's quants for coding and figure out what it uses.

KikoCis

Utopia IA org 6 days ago

•

edited 5 days ago

Unfortunately we don't have the non-quantized weights of this one anymore. Our pipeline deleted them after converting to GGUF, which is a pity.

If you really need them, message me privately and we'll see what we can do. Sounds like an interesting project: follow me on LinkedIn and we'll chat: https://www.linkedin.com/in/kikocis/

Icodetools

about 7 hours ago

I got them! Thank you.

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