Instructions to use empero-ai/Qwen3.8-27B-Ridge-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use empero-ai/Qwen3.8-27B-Ridge-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 empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
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 empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
Use Docker
docker model run hf.co/empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use empero-ai/Qwen3.8-27B-Ridge-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "empero-ai/Qwen3.8-27B-Ridge-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": "empero-ai/Qwen3.8-27B-Ridge-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/empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
- Ollama
How to use empero-ai/Qwen3.8-27B-Ridge-GGUF with Ollama:
ollama run hf.co/empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
- Unsloth Desktop
- Pi
How to use empero-ai/Qwen3.8-27B-Ridge-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
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": "empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use empero-ai/Qwen3.8-27B-Ridge-GGUF with Docker Model Runner:
docker model run hf.co/empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
- Lemonade
How to use empero-ai/Qwen3.8-27B-Ridge-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
Run and chat with the model
lemonade run user.Qwen3.8-27B-Ridge-GGUF-BF16
List all available models
lemonade list
- Hermes Agent
How to use empero-ai/Qwen3.8-27B-Ridge-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 empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
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 empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use empero-ai/Qwen3.8-27B-Ridge-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16
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 "empero-ai/Qwen3.8-27B-Ridge-GGUF:BF16" \ --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"
uncensoring
can we get an uncensored version of this qant ? or at least some help or direction ?
Hey guys! If anyone is still looking for uncensored mixed-precision layout of this architecture,
here is JonathanColetti's abliteration, It uses a similar log-space philosophy to protect the core attention and Mamba SSM layers.
https://huggingface.co/zerodigest/Qwen3.8-27B-Uncensored-YMQ-MTP-GGUF
This one is uncensored already
This one is uncensored already
you mean this ridge variant ?
This one is uncensored already
you mean this ridge variant ?
Yes, you could give it a try
Sorry, I ran some tests and found this ridge‑quantized build isn’t the uncensored one. It still has safety guardrails enabled.
Sorry, I ran some tests and found this ridge‑quantized build isn’t the uncensored one. It still has safety guardrails enabled.
Oh, I only tried use it for red teaming and it worked, so I thought it's uncensored because the original one rejected the same instruction.