Not-For-All-Audiences

Instructions to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-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 marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-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 marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF:Q4_K_M

Ollama
How to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF with Ollama:
```
ollama run hf.co/marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF:Q4_K_M
```

Unsloth Studio

How to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-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 marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-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 marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-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 marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF: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 marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF with OpenClaw:

Start the llama.cpp server

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

Lemonade

How to use marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull marcoariette/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF / README.md

marcoariette

Duplicate from LuffyTheFox/Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF

c5c30f9 4 months ago

preview code

Raw

History Blame Contribute Delete

6.81 kB

metadata

language:
  - en
  - zh
license: apache-2.0
base_model: Qwen/Qwen3.5-9B
tags:
  - unsloth
  - qwen
  - qwen3.5
  - reasoning
  - chain-of-thought
  - lora
  - uncensored
  - not-for-all-audiences
pipeline_tag: text-generation
datasets:
  - Jackrong/Qwen3.5-reasoning-700x
  - nohurry/Opus-4.6-Reasoning-3000x-filtered

🌟 This is Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF model with zero refusals made by HauhauCS method and combined with Jackrong checkpoint

Thinking is disabled by default in this model via modified chat template file baked in gguf. If you want to enable thinking set variable: {%- set enable_thinking = False %} to True in chat template.

I extracted uncensored tensors made by HauhauCS via this script: https://pastebin.com/1qKgR3za and merged them with Jackrong distilled checkpoint.

For best model perfomance use following settings in LM Studio:

Temperature: 0.7

Top K Sampling: 20

Presence Penalty: 1.5

Top P Sampling: 0.8

Min P Sampling: 0

Seed: 3407 or 42

And this system prompt: https://pastebin.com/pU25DVnB

📢 Announcement

Update: This model has been further enhanced with additional reasoning data distilled from Qwen3.5-27B.

The new training data introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.

Part of the data comes from Jackrong/Qwen3.5-reasoning-700x, a curated dataset designed to improve structured step-by-step reasoning and reasoning diversity.

💡 Model Introduction

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled is a highly capable reasoning model fine-tuned on top of the Qwen3.5-9B dense architecture. The model's core directive is to leverage state-of-the-art Chain-of-Thought (CoT) distillation primarily sourced from Claude-4.6 Opus interactions.

Through Supervised Fine-Tuning (SFT) focusing specifically on structured reasoning logic, this model excels in breaking down complex user problems, planning step-by-step methodologies within strictly formatted <think> tags, and ultimately delivering precise, nuanced solutions.

🗺️ Training Pipeline Overview

Base Model (Qwen3.5-9B)
 │
 ▼
Supervised Fine-Tuning (SFT) + LoRA
(Response-Only Training masked on "<|im_start|>assistant\n<think>")
 │
 ▼
Final Model Text-only (Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled)

🧠 Example of Learned Reasoning Scaffold（Example）

The model includes targeted optimizations addressing Qwen3.5’s tendency toward excessive transitional or repetitive reasoning on simple queries. Through deep distillation and structural imitation of Claude-4.6-Opus reasoning chains, the model adopts a more efficient structured thinking pattern:
“Let me analyze this request carefully: 1..2..3...”.
This streamlined reasoning paradigm significantly reduces redundant cognitive loops while preserving deep analytical capacity, resulting in substantially improved inference efficiency.

Let me analyze this request carefully:

1. Identify the core objective of the problem.
2. Break the task into clearly defined subcomponents.
3. Evaluate constraints and edge cases.
4. Formulate a step-by-step solution plan.
5. Execute the reasoning sequentially and verify consistency.
            .
            .
            .

🔹 Supervised Fine-Tuning (SFT)

Objective: To inject high-density reasoning logic and establish a strict format for problem-solving involving an internal thinking state prior to outputting the final response.
Method: We utilized Unsloth for highly efficient memory and compute optimization. A critical component of this stage is the train_on_responses_only strategy, masking instructions so the loss is purely calculated over the generation of the <think> sequences and the subsequent solutions.
Format Enforcement: All training samples were systematically normalized so the model strictly abides by the structure <think> {internal reasoning} </think>\n {final answer}.

📈 Training Loss Curve

The training loss showed a strong and healthy downward trend throughout the run, demonstrating effective knowledge distillation. Starting from an initial loss of 0.5138, the model converged steadily to a final loss of 0.35786 — indicating the model successfully internalized the structured <think> reasoning patterns from the Claude 4.6 Opus teacher data.

📚 All Datasets Used

The dataset consists of high-quality, filtered reasoning distillation data:

Dataset Name	Description / Purpose
nohurry/Opus-4.6-Reasoning-3000x-filtered	Provides comprehensive Claude 4.6 Opus reasoning trajectories.
TeichAI/claude-4.5-opus-high-reasoning-250x	Injecting high-intensity, structured reasoning instances.
Jackrong/Qwen3.5-reasoning-700x	Additional curated reasoning samples designed to strengthen structured step-by-step problem solving and improve reasoning diversity.

🌟 Core Skills & Capabilities

Modular & Structured Thinking: Inheriting traits from Opus-level reasoning, the model demonstrates confident parsing of the prompt, establishing an outlined plan in its <think> block sequentially rather than exploratory "trial-and-error" self-doubt.
Extended Context Support: Fine-tuned smoothly with a 16,384 token context window allowing complex multi-step reasoning traces to exist gracefully within memory limits.

⚠️ Limitations & Intended Use

Hallucination Risk: While reasoning is strong, the model remains an autoregressive LLM; external facts provided during the thinking sequence may occasionally contain hallucinations if verifying real-world events.
Intended Scenario: Best suited for offline analytical tasks, coding, math, and heavy logic-dependent prompting where the user needs to transparently follow the AI's internal logic.

🙏 Acknowledgements

Significant thanks to the Unsloth AI team for making rapid fine-tuning of large LLM models accessible. Additionally, we acknowledge Qwen internally, and the open-source community developers producing exceptional distilled datasets (nohurry and TeichAI).