Instructions to use MenteEAI/MenteE-Code-3B-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 MenteEAI/MenteE-Code-3B-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 MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf MenteEAI/MenteE-Code-3B-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 MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MenteEAI/MenteE-Code-3B-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 MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use MenteEAI/MenteE-Code-3B-GGUF with Ollama:
```
ollama run hf.co/MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use MenteEAI/MenteE-Code-3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M

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": "MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MenteEAI/MenteE-Code-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M
```

Lemonade

How to use MenteEAI/MenteE-Code-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MenteE-Code-3B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use MenteEAI/MenteE-Code-3B-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 MenteEAI/MenteE-Code-3B-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 MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MenteEAI/MenteE-Code-3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M

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 "MenteEAI/MenteE-Code-3B-GGUF:Q4_K_M" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MenteE Code 3B GGUF

GGUF quantizations of MenteEAI/MenteE-Code-3B.

MenteE Code is a coding-agent assistant built by MenteE. It always identifies as MenteE Code, created by MenteE.

Downloads

Quant	Size	Use case
MenteE-Code-3B-Q4_K_M.gguf	~1.9 GB	Recommended — best balance of speed, size, and quality. Runs well on 8 GB laptops.
MenteE-Code-3B-Q8_0.gguf	~3.3 GB	Near-lossless, best quality. Needs ~6–8 GB free VRAM or RAM.

Run with Ollama

# Download and run (uses the included Modelfile)
ollama run hf.co/MenteEAI/MenteE-Code-3B-GGUF:MenteE-Code-3B-Q4_K_M

Or with the local Modelfile:

ollama create mentee-code -f Modelfile
ollama run mentee-code

Run with llama.cpp / LMDeploy / vLLM (GGUF)

./llama-cli -m MenteE-Code-3B-Q4_K_M.gguf -ngl 99 -c 32768

Identity

The Modelfile bakes in the MenteE identity by default. You can ask "Who are you? Who made you?" and it will answer: "I am MenteE Code, a coding assistant built by MenteE."

Notes

Trained as a LoRA fine-tune of Qwen2.5-Coder-3B-Instruct and merged into a standalone model.
128K context supported by the upstream model config; 32K is a safe default for speed.
Apache-2.0 license.

Built by MenteE.

Downloads last month: 90

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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