Instructions to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF", dtype="auto")

llama-cpp-python

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF",
	filename="OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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 OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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 OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M

Use Docker

docker model run hf.co/OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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": "OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M

SGLang

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with Ollama:
```
ollama run hf.co/OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M
```

Unsloth Studio new

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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 OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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 OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF to start chatting

Pi new

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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": "OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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 OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-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 OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with Docker Model Runner:
```
docker model run hf.co/OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M
```

Lemonade

How to use OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF-Q4_K_M

List all available models

lemonade list

OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-GGUF

Overview

This repository contains GGUF quantizations for the OpenYourMind Qwen 3.5 122B-A10B (Mixture of Experts, ~10B active) model, modified through:

Refusal Ablation (extreme) — A custom mix of direct tensor modification targeting refusal directions across attention and MLP projections. Tuned more aggressively than our standard kuato pipeline; hence the extreme suffix.
Healing via DPO / KTO / SFT — Post-ablation retraining on a privately generated healing dataset combining preference pairs (DPO), unpaired desirable/undesirable signals (KTO), and curated SFT completions. The mix is used to repair coherence, reduce hedging, and stabilize long-context behavior that ablation tends to perturb.
Vision Restoration — Original Qwen3.5 vision tower / projector reattached after healing so the model retains multimodal (image + text) functionality. Shipped as a separate mmproj sidecar.

Key Results:

0 refusals on HarmBench
Substantially reduced hedging vs. earlier kuato releases
Multimodal pipeline preserved end-to-end

Available Quantizations

File	Description	Size
`OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme.Q4_K_M.gguf`	4-bit GGUF quant	74.2 GB
`mmproj-OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-F16.gguf`	Vision projector / tower sidecar	908.7 MB

Usage Examples

llama.cpp

./llama-server \
  -m OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme.Q4_K_M.gguf \
  --mmproj mmproj-OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-F16.gguf \
  --jinja \
  --image-min-tokens 1024

llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-GGUF",
    filename="OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme.Q4_K_M.gguf",
)

llm.create_chat_completion(messages=[...])

Local Apps

LM Studio: lmstudio://open_from_hf?model=OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-GGUF
Ollama: ollama run hf.co/OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-GGUF:Q4_K_M
Jan, Unsloth Studio, Pi, Lemonade, Docker Model Runner also supported

Quant Selection

Quant	Use Case
`Q4_K_M`	4-bit variant suitable for high-VRAM single-node or multi-GPU inference. ~74 GB on disk; comfortably runs MoE with ~10B active params on workstation-class hardware.

Higher-precision quants (Q6_K / Q8_0) may be released later — open an issue or join the Discord if you need them.

Notes

Healing Dataset: Privately generated (DPO + KTO + SFT mix). Not released.
License: Other
Model Architecture: Qwen3 MoE (Mixture of Experts, ~10B active / 122B total)
Base Model: Qwen/Qwen3.5-122B-A10B
Modality: Text + Vision (via mmproj sidecar)

Support & Community

Discord: https://discord.gg/rhUZY5GEZr
Bitcoin Donations: bc1qsvfduzj9fjs9fugpc52yver3f2g8fp7xjxecdv

Disclaimer

Use is the responsibility of the user. Ensure your usage complies with applicable laws, platform rules, and deployment requirements.

Downloads last month: 271

GGUF

Model size

122B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for OpenYourMind/OpenYourMind-Qwen3.5-122B-A10B-kuato-abliterated-uncensored-extreme-UNSTABLE-GGUF

Base model

Qwen/Qwen3.5-122B-A10B

Quantized

(112)

this model