Instructions to use BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1 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-Turbo-AbliteratedV1 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-Turbo-AbliteratedV1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1: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-Turbo-AbliteratedV1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1: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-Turbo-AbliteratedV1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1: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-Turbo-AbliteratedV1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1:Q4_K_M

Use Docker

docker model run hf.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1:Q4_K_M

LM Studio
Jan
Ollama
How to use BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1 with Ollama:
```
ollama run hf.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1:Q4_K_M
```
Unsloth Desktop

How to use BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1 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-Turbo-AbliteratedV1: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": "BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1 with Docker Model Runner:
```
docker model run hf.co/BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1:Q4_K_M
```

Lemonade

How to use BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4b-Z-Image-Turbo-AbliteratedV1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1 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-Turbo-AbliteratedV1: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-Turbo-AbliteratedV1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use BennyDaBall/Qwen3-4b-Z-Image-Turbo-AbliteratedV1 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-Turbo-AbliteratedV1: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-Turbo-AbliteratedV1: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"

BennyDaBall commited on Jan 28

Commit

f35dd61

verified ·

1 Parent(s): d174c0a

Update README with correct base model

Browse files

Files changed (1) hide show

README.md +5 -4

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: Qwen/Qwen2.5-Coder-32B-Instruct
 tags:
 - abliterated
 - heretic
@@ -15,11 +15,11 @@ tags:
 Welcome to the ablation station! 🚂💨
-This is the **abliterated** version of the Z-Image-Turbo text encoder. We took the **p-e-w heretic method** and hammered it through **1000 trials**, specifically targeting **BOTH** image generation refusals and those peskier general refusals.
 The result?
 - **KL Divergence:** A tiny `0.0004` (basically no lobotomy! 🧠✨)
-- **Refusal Rate:** Only `4/100` in our torture tests.
 It's ready to generate what you want, when you want it.
@@ -28,4 +28,5 @@ Brought to you by the same chaotic good energy behind:
 - [Z-Image-Engineer-V2.5](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Engineer-V2.5)
 - The original [Z-Image-Engineer](https://huggingface.co/BennyDaBall/qwen3-4b-Z-Image-Engineer)
-Enjoy responsibly (or irresponsibly, I'm a model weighting file, not a cop).

 ---
 license: apache-2.0
+base_model: Tongyi-MAI/Z-Image-Turbo
 tags:
 - abliterated
 - heretic
 Welcome to the ablation station! 🚂💨
+This is the **abliterated** version of the Z-Image-Turbo text encoder. I took the **p-e-w heretic method** and hammered it through **1000 trials**, specifically targeting **BOTH** image generation refusals and those peskier general refusals.
 The result?
 - **KL Divergence:** A tiny `0.0004` (basically no lobotomy! 🧠✨)
+- **Refusal Rate:** Only `4/100` in my torture tests.
 It's ready to generate what you want, when you want it.
 - [Z-Image-Engineer-V2.5](https://huggingface.co/BennyDaBall/Qwen3-4b-Z-Image-Engineer-V2.5)
 - The original [Z-Image-Engineer](https://huggingface.co/BennyDaBall/qwen3-4b-Z-Image-Engineer)
+## Disclaimer
+I am not responsible for what you create with this model. This is a model weighting file, not a moral compass. You are responsible for your own outputs and following local laws. Use this power wisely.