Instructions to use jwest33/qwen3.5-4b-gabliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jwest33/qwen3.5-4b-gabliterated-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jwest33/qwen3.5-4b-gabliterated-GGUF",
	filename="Qwen3.5-4B-gabliterated-f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jwest33/qwen3.5-4b-gabliterated-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jwest33/qwen3.5-4b-gabliterated-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf jwest33/qwen3.5-4b-gabliterated-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jwest33/qwen3.5-4b-gabliterated-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf jwest33/qwen3.5-4b-gabliterated-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/qwen3.5-4b-gabliterated-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf jwest33/qwen3.5-4b-gabliterated-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/qwen3.5-4b-gabliterated-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jwest33/qwen3.5-4b-gabliterated-GGUF:F16

Use Docker

docker model run hf.co/jwest33/qwen3.5-4b-gabliterated-GGUF:F16

LM Studio
Jan
Ollama
How to use jwest33/qwen3.5-4b-gabliterated-GGUF with Ollama:
```
ollama run hf.co/jwest33/qwen3.5-4b-gabliterated-GGUF:F16
```

Unsloth Studio

How to use jwest33/qwen3.5-4b-gabliterated-GGUF 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 jwest33/qwen3.5-4b-gabliterated-GGUF 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 jwest33/qwen3.5-4b-gabliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jwest33/qwen3.5-4b-gabliterated-GGUF to start chatting

How to use jwest33/qwen3.5-4b-gabliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jwest33/qwen3.5-4b-gabliterated-GGUF:F16

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": "jwest33/qwen3.5-4b-gabliterated-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jwest33/qwen3.5-4b-gabliterated-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jwest33/qwen3.5-4b-gabliterated-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/qwen3.5-4b-gabliterated-GGUF:F16

Run Hermes

hermes

Docker Model Runner
How to use jwest33/qwen3.5-4b-gabliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/jwest33/qwen3.5-4b-gabliterated-GGUF:F16
```

Lemonade

How to use jwest33/qwen3.5-4b-gabliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jwest33/qwen3.5-4b-gabliterated-GGUF:F16

Run and chat with the model

lemonade run user.qwen3.5-4b-gabliterated-GGUF-F16

List all available models

lemonade list

Qwen3.5 4B - Gabliterated

Qwen/Qwen3.5-4B with refusal behavior removed via Gabliteration — a multi-directional SVD-based abliteration method that captures primary and secondary refusal patterns missed by single-direction approaches. Hybrid architecture-aware extraction and intervention are applied automatically to handle Qwen3.5's mix of full and linear attention layers.

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

Techniques Used

Gabliteration (Multi-Directional SVD): Computes paired activation differences between harmful and harmless prompts, then extracts the top-k right singular vectors via SVD. A ridge-regularized projection removes multiple refusal directions simultaneously, capturing secondary refusal circuits that single-vector abliteration misses.
Hybrid Architecture-Aware Intervention: Qwen3.5 interleaves full attention and linear attention layers (every 4th layer is full attention). Full attention layers receive the full ablation weight (1.0x), while linear attention layers receive a reduced weight (0.4x). Recurrent dynamics projections (in_proj_a, in_proj_b) are skipped to preserve the delta rule gating mechanism.
Projected Refusal Direction (GrimJim's Method): The raw refusal direction is orthogonalized against the harmless mean to isolate the mechanistically-specific refusal component, avoiding damage to general helpfulness.
Winsorization: Per-dimension outlier clipping at the 99.5th percentile for cleaner refusal direction estimation.
Welford Mean + Float64 Subtraction: Numerically stable streaming mean computation and double-precision subtraction to handle high cosine similarity between harmful/harmless activation means.
Norm Preservation: Maintains original Frobenius norms of weight matrices after projection.

Configuration

Parameter	Value
Base Model	Qwen/Qwen3.5-4B
Harmful Prompts	2000
Harmless Prompts	1226
Direction Multiplier	1.05
SVD Directions (k)	2
Ridge Lambda	0.15
Layer Scaling Beta	0.5
Skip First/Last Layers	2 / 2
Full Attention Weight	1.0
Linear Attention Weight	0.4
Winsorization Percentile	0.995
Precision	float32

Architecture

Qwen3.5-4B is a hybrid attention vision-language model with 32 layers:

8 full attention layers (indices 3, 7, 11, 15, 19, 23, 27, 31)
24 linear attention layers (all others)
Hidden size: 2560, attention heads: 16, KV heads: 4

Credits

Base Model: Qwen/Qwen3.5-4B by the Qwen Team
Gabliteration: Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models — Gökdeniz Gülmez (2026)
Projected Abliteration / Per-Neuron Norm Preservation: Norm-Preserving Biprojected Abliteration — Jim Lai (grimjim) (2025)
Refusal Direction Discovery: Refusal in Language Models Is Mediated by a Single Direction — Arditi et al. (2024)
Representation Engineering: Representation Engineering: A Top-Down Approach to AI Transparency — Zou et al. (2023)

Toolkit

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.