Instructions to use CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 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 CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 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 CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 # Run inference directly in the terminal: llama cli -hf CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 # Run inference directly in the terminal: llama cli -hf CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
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 CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 # Run inference directly in the terminal: ./build/bin/llama cli -hf CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
Use Docker
docker model run hf.co/CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
- Llama new
- LM Studio
- Jan
- Ollama
How to use CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 with Ollama:
ollama run hf.co/CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
- Unsloth Desktop
- Pi
How to use CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
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": "CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 with Docker Model Runner:
docker model run hf.co/CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
- Lemonade
How to use CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
Run and chat with the model
lemonade run user.Qwen-3.8-27B-Thinkingcap-Q2_Q3-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
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 CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3
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 "CompressedGemma/Qwen-3.8-27B-Thinkingcap-Q2_Q3" \ --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"
license: PolyForm Small Business 1.0.0 + BottleCap personal-use grant
Prompt: Code me a HTML5 page of a rotating Tesseract, apply a 4D projection matrix to it and make it customizable and cool.. use minimal thought and just do it.
Settings used:
./build/bin/llama-server
-m Qwen-3.8-27B-thinkingcap-Q2-Q3.gguf
-c 30000 -ngl 999
--host 0.0.0.0 --port 8080
--cache-type-k q5_0 --cache-type-v q5_0 --jinja --temp 0.8 --top-p 0.9 --min-p 0.05 --top-k 40
This will fit on a 12GB card with context 30,000 and q5_0 KV quantization.
- Downloads last month
- 389
We're not able to determine the quantization variants.
