- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
Use Docker
docker model run hf.co/timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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": "timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'Use Docker
docker model run hf.co/timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
- Ollama
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF with Ollama:
ollama run hf.co/timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
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:8080/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M"
}
]
}
}
}Run Pi
# Start Pi in your project directory:
pi
- Docker Model Runner
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF with Docker Model Runner:
docker model run hf.co/timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
- Lemonade
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/
lemonade pull timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-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 timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-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 "timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-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"
