Instructions to use BennyDaBall/qwen3-4b-Z-Image-Engineer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use BennyDaBall/qwen3-4b-Z-Image-Engineer 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 BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BennyDaBall/qwen3-4b-Z-Image-Engineer: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 BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BennyDaBall/qwen3-4b-Z-Image-Engineer: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 BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M

Use Docker

docker model run hf.co/BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M

LM Studio
Jan
Ollama
How to use BennyDaBall/qwen3-4b-Z-Image-Engineer with Ollama:
```
ollama run hf.co/BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M
```

Unsloth Studio

How to use BennyDaBall/qwen3-4b-Z-Image-Engineer 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 BennyDaBall/qwen3-4b-Z-Image-Engineer 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 BennyDaBall/qwen3-4b-Z-Image-Engineer to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BennyDaBall/qwen3-4b-Z-Image-Engineer to start chatting

How to use BennyDaBall/qwen3-4b-Z-Image-Engineer with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use BennyDaBall/qwen3-4b-Z-Image-Engineer with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BennyDaBall/qwen3-4b-Z-Image-Engineer: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 "BennyDaBall/qwen3-4b-Z-Image-Engineer: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"

Docker Model Runner
How to use BennyDaBall/qwen3-4b-Z-Image-Engineer with Docker Model Runner:
```
docker model run hf.co/BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M
```

Lemonade

How to use BennyDaBall/qwen3-4b-Z-Image-Engineer with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-4b-Z-Image-Engineer-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use BennyDaBall/qwen3-4b-Z-Image-Engineer with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BennyDaBall/qwen3-4b-Z-Image-Engineer: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 BennyDaBall/qwen3-4b-Z-Image-Engineer:Q4_K_M

Run Hermes

hermes

Atomic Chat

re The "Camera" Fix

by HuggyBear96 - opened Jan 30

Discussion

HuggyBear96

Jan 30

I find the same is true for drones. When describing a scene with a 'drone view of...' the resulting image has a drone in the image.

BennyDaBall

Owner Jan 30

Good catch. This has been fixed in V2.5+ - I got rid of the camera specification in the output entirely - it will now render top down drone shot images when asked. It wasn't trained on "drone" nomenclature, so 'birds eye view perspective' is more consistent if you are looking for an aerial shot!

You can system prompt around the camera/drone/lighting glitch with a negative constraint with positive constraint alternative, eg.

'Never include the camera/drone/light device itself, studio lights or stands, camera body, propellers, or quadcopter body within the frame, nor any text or camera model names referencing specific drone brands like DJI in your output. Use positive constraints to describe the aesthetic produced from the camera/drone/lighting like 'birds-eye view,' 'high-altitude aerial,' 'top-down perspective,' or 'soft studio illumination,' to ensure the model focuses on the visual style and angle rather than rendering the hardware.'

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