Dockerfile

FROM ghcr.io/ggml-org/llama.cpp:full

WORKDIR /app

RUN apt update && apt install -y python3 python3-pip python3-venv
RUN python3 -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

RUN pip install -U pip huggingface_hub

RUN python3 -c 'from huggingface_hub import hf_hub_download; \
    repo="rahul7star/gemma-gguf"; \
    hf_hub_download(repo_id=repo, filename="model-gemma4-heretic-apexi-quality.gguf", local_dir="/app")'

CMD ["--server", \
     "-m", "/app/model-gemma4-heretic-apexi-quality.gguf", \
     "--host", "0.0.0.0", \
     "--port", "7860", \
     "-t", "2", \
     "--cache-type-k", "q8_0", \
     "--cache-type-v", "iq4_nl", \
     "-c", "96000", \
     "-n", "38912"]