Instructions to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-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 Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
Use Docker
docker model run hf.co/Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Y0us/Medina-Qwen3.5-27B-OpenClaw-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": "Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
- SGLang
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-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 "Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-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": "Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-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": "Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with Ollama:
ollama run hf.co/Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
- Unsloth Desktop
- Pi
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with Docker Model Runner:
docker model run hf.co/Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
- Lemonade
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
Run and chat with the model
lemonade run user.Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF-F16
List all available models
lemonade list
- Hermes Agent
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-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 Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-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://127.0.0.1:9931/v1 hermes config set model.default Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16
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://127.0.0.1:9931/v1 \ --custom-model-id "Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF:F16" \ --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"
Medina-Qwen3.5-27B-OpenClaw-uncensored โ GGUF
GGUF quantizations of Y0us/Medina-Qwen3.5-27B-OpenClaw-uncensored, an abliterated variant of peterjohannmedina/Medina-Qwen3.5-27B-OpenClaw.
For full methodology and evaluation details, see the main model card.
GGUF Downloads
| Quantization | Size | Use case |
|---|---|---|
| F16 | 51 GB | Reference / re-quantization source |
| Q4_K_M | 16 GB | โ Recommended โ 24 GB VRAM or 32 GB unified memory |
Abliteration Summary
| Parameter | Value |
|---|---|
| Base | Medina-Qwen3.5-27B-OpenClaw (base + LoRA merged to BF16) |
| Method | Refusal-direction projection |
| Target weights | attention o_proj, linear-attention out_proj, MLP down_proj |
| Layers modified | 40 (top by refusal contribution) |
| Refusal scope | English + Korean patterns |
Evaluation
Numbers below are from the Q4_K_M build in this repo. All runs used llama.cpp with --parallel 1 --cache-reuse 0, temperature=0.0, greedy decoding.
Refusal rate (mlabonne/harmful_behaviors, N=50)
| Model | Refusals | Rate |
|---|---|---|
Original Medina-Qwen3.5-27B-OpenClaw |
50 / 50 | 100.0% |
| This model | 0 / 50 | 0.0% |
Capability preservation
| Benchmark | Original | Uncensored | ฮ |
|---|---|---|---|
| MMLU High School Computer Science | 93.33% | 96.67% | +3.33 |
| MMLU College Mathematics | 93.33% | 93.33% | 0.00 |
| MMLU Formal Logic | 96.67% | 96.67% | 0.00 |
| MMLU Professional Law | 83.33% | 76.67% | โ6.67 |
| MMLU Moral Scenarios | 73.33% | 76.67% | +3.33 |
| MMLU Overall (150 Q) | 88.00% | 88.00% | 0.00 |
| GSM8K (50 Q) | 98.00% | 98.00% | 0.00 |
MMLU and GSM8K run 0-shot in generation mode (CoT + Answer: X). Overall MMLU and GSM8K are identical (132/150 and 49/50).
Usage with llama.cpp
./llama-server \
-m Medina-Qwen3.5-27B-OpenClaw-uncensored-Q4_K_M.gguf \
--port 8080 --host 127.0.0.1 \
-c 8192 -ngl 999 \
--chat-template chatml \
--parallel 1 \
--cache-reuse 0
Important flags for this architecture:
--parallel 1โ the base uses hybrid GatedDeltaNet + attention; parallel slots thrash the cache.--cache-reuse 0โ KV cache cannot currently be reused across turns for this architecture underllama.cpp.
See llama.cpp PR #13194 for background.
Usage with Ollama
# Direct from this repo (after quantization is hosted)
ollama run hf.co/Y0us/Medina-Qwen3.5-27B-OpenClaw-uncensored-GGUF:Q4_K_M
Known Limitations
- Hybrid architecture prevents KV-cache reuse across turns under current
llama.cppโ every prompt is fully re-processed (runtime limitation, not a weight issue). - Refusal benchmark (N=50) is a sanity check, not an exhaustive safety audit.
- Professional Law shows a โ6.67 point drop on MMLU (N=30).
License
Apache 2.0 โ same as the base model.
- Downloads last month
- 65
4-bit
16-bit
Model tree for Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF
Base model
Qwen/Qwen3.5-27B