Instructions to use wingman-llc/WINGMAN-OPENS-0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use wingman-llc/WINGMAN-OPENS-0.2 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 wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wingman-llc/WINGMAN-OPENS-0.2: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 wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf wingman-llc/WINGMAN-OPENS-0.2: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 wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M

Use Docker

docker model run hf.co/wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M

LM Studio
Jan

vLLM

How to use wingman-llc/WINGMAN-OPENS-0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wingman-llc/WINGMAN-OPENS-0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wingman-llc/WINGMAN-OPENS-0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M

Ollama
How to use wingman-llc/WINGMAN-OPENS-0.2 with Ollama:
```
ollama run hf.co/wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M
```
Unsloth Desktop

How to use wingman-llc/WINGMAN-OPENS-0.2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wingman-llc/WINGMAN-OPENS-0.2: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": "wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use wingman-llc/WINGMAN-OPENS-0.2 with Docker Model Runner:
```
docker model run hf.co/wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M
```

Lemonade

How to use wingman-llc/WINGMAN-OPENS-0.2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M

Run and chat with the model

lemonade run user.WINGMAN-OPENS-0.2-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use wingman-llc/WINGMAN-OPENS-0.2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wingman-llc/WINGMAN-OPENS-0.2: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 wingman-llc/WINGMAN-OPENS-0.2:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use wingman-llc/WINGMAN-OPENS-0.2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wingman-llc/WINGMAN-OPENS-0.2: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 "wingman-llc/WINGMAN-OPENS-0.2: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"

WINGMAN-OPENS 0.2

A lightweight, locally runnable AI model for conversation and coding.

WINGMAN-OPENS 0.2 is an experimental language model developed by WINGMAN LLC in England. It's designed for English-language conversations, programming assistance, and code generation, with a focus on running locally through Ollama.

Model Information

Name: WINGMAN-OPENS 0.2
Developer: WINGMAN LLC
Location: England
Release date: October 24, 2026
Parameters: Approximately 500 million
Model size: Approximately 379 MB
Format: GGUF
Quantization: Q4_K_M
Primary language: English
Fine-tuning method: LoRA
Training dataset: 1,200 examples from UltraChat
Training duration: 1 epoch
Reported training loss: Approximately 2.0449
License: Apache-2.0

What Can It Do?

WINGMAN-OPENS is intended for lightweight, everyday use and experimentation.

Hold basic English conversations
Help with programming questions
Generate and explain code
Run locally using Ollama
Operate without sending prompts to a hosted inference service, when used entirely locally

Its relatively small size makes it an accessible starting point for people interested in running and experimenting with language models on their own hardware.

Downloads last month: 24

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

4-bit