Dockerfile

FROM python:3.10-slim

RUN apt-get update && apt-get install -y wget build-essential && rm -rf /var/lib/apt/lists/*

RUN pip install --no-cache-dir llama-cpp-python[server] huggingface_hub

RUN wget https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF/resolve/main/gemma-4-E4B-it-Q4_K_M.gguf -O /model.gguf

ENV HOST=0.0.0.0
ENV PORT=7860

EXPOSE 7860

CMD ["python3", "-m", "llama_cpp.server", "--model", "/model.gguf", "--host", "0.0.0.0", "--port", "7860", "--n_ctx", "4096"]