How to use 56m/MathQwen_2 with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf 56m/MathQwen_2 # Run inference directly in the terminal: llama cli -hf 56m/MathQwen_2
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf 56m/MathQwen_2 # Run inference directly in the terminal: llama cli -hf 56m/MathQwen_2
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 56m/MathQwen_2 # Run inference directly in the terminal: ./build/bin/llama cli -hf 56m/MathQwen_2
docker model run hf.co/56m/MathQwen_2
How to use 56m/MathQwen_2 with Ollama:
ollama run hf.co/56m/MathQwen_2
How to use 56m/MathQwen_2 with Docker Model Runner:
How to use 56m/MathQwen_2 with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull 56m/MathQwen_2
lemonade run user.MathQwen_2-{{QUANT_TAG}}
lemonade list
