Instructions to use mdaiworks/yengi-router-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mdaiworks/yengi-router-1.5b 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 mdaiworks/yengi-router-1.5b
# Run inference directly in the terminal:
llama cli -hf mdaiworks/yengi-router-1.5b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mdaiworks/yengi-router-1.5b
# Run inference directly in the terminal:
llama cli -hf mdaiworks/yengi-router-1.5b

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 mdaiworks/yengi-router-1.5b
# Run inference directly in the terminal:
./llama-cli -hf mdaiworks/yengi-router-1.5b

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 mdaiworks/yengi-router-1.5b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mdaiworks/yengi-router-1.5b

Use Docker

docker model run hf.co/mdaiworks/yengi-router-1.5b

LM Studio
Jan

vLLM

How to use mdaiworks/yengi-router-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mdaiworks/yengi-router-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mdaiworks/yengi-router-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mdaiworks/yengi-router-1.5b

Ollama
How to use mdaiworks/yengi-router-1.5b with Ollama:
```
ollama run hf.co/mdaiworks/yengi-router-1.5b
```
Unsloth Desktop

How to use mdaiworks/yengi-router-1.5b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mdaiworks/yengi-router-1.5b

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": "mdaiworks/yengi-router-1.5b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mdaiworks/yengi-router-1.5b with Docker Model Runner:
```
docker model run hf.co/mdaiworks/yengi-router-1.5b
```

Lemonade

How to use mdaiworks/yengi-router-1.5b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mdaiworks/yengi-router-1.5b

Run and chat with the model

lemonade run user.yengi-router-1.5b-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use mdaiworks/yengi-router-1.5b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mdaiworks/yengi-router-1.5b

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 mdaiworks/yengi-router-1.5b

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mdaiworks/yengi-router-1.5b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mdaiworks/yengi-router-1.5b

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 "mdaiworks/yengi-router-1.5b" \
  --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"

🚀 Yengi Router 1.5B (GGUF)

Yengi Router 1.5B is a lightweight and fast Local Intent & Task Routing model specifically optimized for Yengi, an AI-powered coding assistant.

Built on the Qwen 2.5 1.5B architecture, this model analyzes user prompts and determines locally, within milliseconds, which AI provider, tool, or coding mode should handle the request.

📌 Model Information

Developer: mdaiworks
Model Type: GGUF (Quantized)
Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct
Quantization: Q4_K_M (4-bit)
License: Apache 2.0
Target Application: Yengi IDE

⚙️ Usage

1. Automatic Download with Yengi IDE (Recommended)

In Yengi IDE, go to Settings > Local Router (Ollama) and click the "Download Yengi Router" button to automatically download and configure the model in your application.

2. Run Manually with Ollama

To run the downloaded .gguf file with Ollama:

# Create a Modelfile
echo "FROM ./yengi-router-Coder-1.5b-q4.gguf" > Modelfile

# Create the Ollama model
ollama create yengi-router:1.5b -f Modelfile

# Test the model
ollama run yengi-router:1.5b

3. Step: Making the Repository Public

After uploading the model file and saving the Model Card, click the Settings tab at the top of the page.
Scroll down to the Danger Zone section and click Change visibility.
Set the repository visibility to Public.

4. Step: Final Configuration

Code Updated: The download URL in the Yengi IDE code has been updated to:

https://huggingface.co/mdaiworks/yengi-router-1.5b/resolve/main/yengi-router-1.5b-q4.gguf

The project has been successfully built with the updated URL. Once you make the repository Public, the download button in Yengi IDE will directly download the model file from this repository.

Downloads last month: 114

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants