llama.cpp How to use sayhan/gemma-2b-GGUF-quantized 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 sayhan/gemma-2b-GGUF-quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sayhan/gemma-2b-GGUF-quantized:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sayhan/gemma-2b-GGUF-quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sayhan/gemma-2b-GGUF-quantized: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 sayhan/gemma-2b-GGUF-quantized:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sayhan/gemma-2b-GGUF-quantized: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 sayhan/gemma-2b-GGUF-quantized:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sayhan/gemma-2b-GGUF-quantized:Q4_K_M
Use Docker
docker model run hf.co/sayhan/gemma-2b-GGUF-quantized:Q4_K_M
docker model run hf.co/sayhan/gemma-2b-GGUF-quantized: