How to use valencar/llamm with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf valencar/llamm:Q5_0 # Run inference directly in the terminal: llama cli -hf valencar/llamm:Q5_0
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf valencar/llamm:Q5_0 # Run inference directly in the terminal: llama cli -hf valencar/llamm:Q5_0
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 valencar/llamm:Q5_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf valencar/llamm:Q5_0
docker model run hf.co/valencar/llamm:Q5_0
How to use valencar/llamm with Ollama:
ollama run hf.co/valencar/llamm:Q5_0
How to use valencar/llamm with Docker Model Runner:
How to use valencar/llamm with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull valencar/llamm:Q5_0
lemonade run user.llamm-Q5_0
lemonade list
5-bit
