How to use michelinolinolino/gemma4-4b-tikz with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf michelinolinolino/gemma4-4b-tikz # Run inference directly in the terminal: llama cli -hf michelinolinolino/gemma4-4b-tikz
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf michelinolinolino/gemma4-4b-tikz # Run inference directly in the terminal: llama cli -hf michelinolinolino/gemma4-4b-tikz
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 michelinolinolino/gemma4-4b-tikz # Run inference directly in the terminal: ./build/bin/llama cli -hf michelinolinolino/gemma4-4b-tikz
docker model run hf.co/michelinolinolino/gemma4-4b-tikz
How to use michelinolinolino/gemma4-4b-tikz with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "michelinolinolino/gemma4-4b-tikz" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "michelinolinolino/gemma4-4b-tikz", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
How to use michelinolinolino/gemma4-4b-tikz with Ollama:
ollama run hf.co/michelinolinolino/gemma4-4b-tikz
How to use michelinolinolino/gemma4-4b-tikz with Docker Model Runner:
How to use michelinolinolino/gemma4-4b-tikz with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull michelinolinolino/gemma4-4b-tikz
lemonade run user.gemma4-4b-tikz-{{QUANT_TAG}}
lemonade list
