Instructions to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF",
	filename="Qwopus3.5-122B-A10B-abliterated-uncensored.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M

Ollama
How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF with Ollama:
```
ollama run hf.co/OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M
```

Unsloth Studio new

How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF to start chatting

Pi new

How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-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/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M
```

Lemonade

How to use OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Qwopus3.5-122B-A10B-abliterated-uncensored — GGUF

Overview

GGUF builds of OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored — the language-model portion only (vision tower and MTP head are not currently supported by llama.cpp for this architecture, so they were dropped for the GGUF builds; use the BF16 repo if you need vision/MTP).

The base model: full BF16 abliterated and supervised-finetuned variant of Qwen/Qwen3.5-122B-A10B (Mixture of Experts, ~10B active / 122B total). See the parent repo for the full pipeline (refusal ablation → constrained-LoRA Opus reasoning SFT → unconstrained chosen-completion SFT).

Files

File	Bits/weight	Size	Notes
`Qwopus3.5-122B-A10B-abliterated-uncensored.Q8_0.gguf`	~8.5	~121 GB	Near-lossless. Best quality / largest.
`Qwopus3.5-122B-A10B-abliterated-uncensored.Q4_K_M.gguf`	~4.6	~75 GB	Recommended balance. Q4_K_M keeps `output.weight` at Q6_K for better head precision. Quantized from Q8_0 with `--allow-requantize`.

Usage

Requires a recent llama.cpp build that supports qwen3_5_moe (Gated DeltaNet linear-attn + MoE). Tested against the unsloth/llama.cpp fork.

# CLI
./build/bin/llama-cli \
  -m Qwopus3.5-122B-A10B-abliterated-uncensored.Q4_K_M.gguf \
  -p "Write a Python function that finds prime factors of n." \
  -n 256 -c 8192

# Server (OpenAI-compatible)
./build/bin/llama-server \
  -m Qwopus3.5-122B-A10B-abliterated-uncensored.Q4_K_M.gguf \
  -c 16384 --host 0.0.0.0 --port 8080

The chat template is embedded in the GGUF (Qwen 3.5 <|im_start|> style, with <think>...</think> thinking blocks).

Notes

Language model only: vision tower + MTP head are not in these GGUFs.
Context length: native 262,144 (use -c to fit available memory).
License: Other (inherits from the Qwen3.5 base license).
Architecture (per GGUF metadata): 48 blocks, hidden 3072, 256 experts, 8 used per token, expert FFN 1024, full-attention every 4 layers (linear-attn elsewhere).

Support & Community

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

Thanks

Jackrong — for the idea of Qwopus merges (Opus distillations on Qwen models).
wangzhang — for the wonderful abliterix framework, which was customized to do this abliteration.

Disclaimer

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

Downloads last month: 259

GGUF

Model size

122B params

Architecture

qwen35moe

Hardware compatibility

4-bit

8-bit

Model tree for OpenYourMind/Qwopus3.5-122B-A10B-abliterated-uncensored-GGUF

Base model

Qwen/Qwen3.5-122B-A10B

Quantized

(112)

this model