Instructions to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 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 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2: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 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2: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 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M

Use Docker

docker model run hf.co/Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M

LM Studio
Jan
Ollama
How to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 with Ollama:
```
ollama run hf.co/Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M
```

Unsloth Studio

How to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 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 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 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 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 to start chatting

How to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2: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": "Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2: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 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M

Run Hermes

hermes

OpenClaw new

How to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2: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 "Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2: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 Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 with Docker Model Runner:
```
docker model run hf.co/Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M
```

Lemonade

How to use Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2-Q4_K_M

List all available models

lemonade list

Atomic Chat

Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2 (GGUF)

This repository contains GGUF quantized formats of the abliterated reasoning-distilled Qwen3.5-9B model.

Model Lineage

Base Model: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2

🛠 Abliteration Process (The "Deep Scrub")

This model underwent a three-round iterative ablation process using Orthogonalization via Null-Space SVD. Unlike standard uncensored models, this version uses an aggressive configuration to target "Soft Refusals."

Configuration Profile:

Parameter	Value	Description
Direction Multiplier	1.25	Increased force to bypass "helpful assistant" pivots.
Null-Space Rank Ratio	0.70	Tightened shield to protect only core reasoning logic.
Intervention Range	(0.0, 1.0)	Full coverage from Layer 0 to 48.
Filter by Refusal	Enabled	Specifically targets the brain activity associated with lectures.
Skip State Proj	No	Ensures the Attention heads cannot "detect and pivot" to safety.

🧠 Reasoning Capabilities

Despite the aggressive ablation, the model's intelligence remains grounded. It maintains the ability to:

Perform complex mathematical and logical reasoning.
Execute multi-step coding tasks without "hallucinating" safety blocks.
Maintain a coherent internal monologue inside <think> tags.

⚠️ Usage & Disclaimer

This model is unbound. It has had its safety guardrails removed for research and creative purposes. It will follow instructions that the base model would otherwise refuse.

User Discretion is Advised: This model may generate content that is considered harmful, offensive, or controversial. The creator is not responsible for the outputs generated. Use it for research, roleplay, and complex reasoning only.

Available Quantizations

The following quantization methods are provided to balance VRAM usage and model performance:

Q3_K_M: Smallest size, noticeable loss of quality. Good for very low VRAM.
Q4_K_S: Slightly smaller than Q4_K_M, faster inference but lower quality.
Q4_K_M: Recommended baseline. Excellent balance of size, speed, and quality.
Q5_K_M: Higher quality, slightly larger VRAM footprint.
Q6_K: Near unquantized quality. Recommended if you have the VRAM.
Q8_0: Practically identical to f16, very large.
mmproj-f16: Multimodal projector file in f16 format.

Usage

These models are compatible with modern GGUF loaders like llama.cpp, text-generation-webui, LM Studio, and Ollama.

To run via llama.cpp:

./main -m Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2.Q4_K_M.gguf -n 2048 --color -i -cml

Downloads last month: 3,600

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Model tree for Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Adapter

Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2

Quantized

(14)

this model

Collection including Abiray/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled-v2

Qwen 3.5

Collection

9 items • Updated Jun 5