Instructions to use jwest33/qwen3.5-9b-null-space-abliterated-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 jwest33/qwen3.5-9b-null-space-abliterated-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 jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

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 jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

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 jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

Use Docker

docker model run hf.co/jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

LM Studio
Jan
Ollama
How to use jwest33/qwen3.5-9b-null-space-abliterated-GGUF with Ollama:
```
ollama run hf.co/jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16
```
Unsloth Desktop

How to use jwest33/qwen3.5-9b-null-space-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

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": "jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jwest33/qwen3.5-9b-null-space-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16
```

Lemonade

How to use jwest33/qwen3.5-9b-null-space-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

Run and chat with the model

lemonade run user.qwen3.5-9b-null-space-abliterated-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use jwest33/qwen3.5-9b-null-space-abliterated-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 jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

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 jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jwest33/qwen3.5-9b-null-space-abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16

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 "jwest33/qwen3.5-9b-null-space-abliterated-GGUF:F16" \
  --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"

Qwen3.5 9B - Null-Space Abliterated

Qwen/Qwen3.5-9B with refusal behavior removed via orthogonal projection. Uses null-space constraints and adaptive layer weighting to preserve model capabilities.

Important: This model will produce uncensored outputs. Use responsibly.

Note: Version 20260303 (Low Quality) - There will likely be more versions after more thorough experimentation with hybrid weighting to boost reasoning.

Abliteration Techniques Used

Winsorization: Clips outlier activations at the 99th percentile for cleaner refusal direction estimation
Null-Space Projection: Preserves model capabilities by constraining weight updates to the null space of preservation activations
Adaptive Weighting: Applies Gaussian-weighted per-layer ablation strength, focusing on middle-to-later layers where refusal behavior concentrates
Norm Preservation: Maintains original Frobenius norms of weight matrices after projection

Parameter	Value
Harmful Prompts	1000
Harmless Prompts	1000
Full Attention Weight	1.0
Linear Attention Weight	0.4
Direction Multiplier	1.3
Null-Space Constraints	rank ratio: 0.7
Winsorization Percentile	0.995

Credits

Base Model: Qwen/Qwen3.5-9B by Qwen Team
Norm-Preserving Biprojected Abliteration — Jim Lai (grimjim) (2025)
AlphaEdit: Null-Space Constrained Knowledge Editing — Fang et al. (ICLR 2025)
Refusal in Language Models Is Mediated by a Single Direction — Arditi et al. (2024)
Representation Engineering — Zou et al. (2023)

Toolkit Used

github.com/jwest33/abliterator

License

This model inherits the Apache 2.0 license from the base model.

Disclaimer

This model is provided for research and educational purposes. The creators are not responsible for any misuse. Users are solely responsible for ensuring their use complies with applicable laws and ethical standards.

Downloads last month: 280

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for jwest33/qwen3.5-9b-null-space-abliterated-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(521)

this model

Papers for jwest33/qwen3.5-9b-null-space-abliterated-GGUF