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

WORKDIR /app

RUN apt-get update && apt-get install -y --no-install-recommends python3-pip python3-venv && rm -rf /var/lib/apt/lists/*

RUN python3 -m venv /opt/venv
ENV PATH=/opt/venv/bin:$PATH

RUN pip install --no-cache-dir -U huggingface_hub

RUN python3 -c 'from huggingface_hub import hf_hub_download; hf_hub_download(repo_id="yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF", filename="gemma4-coding-Q4_K_M.gguf", local_dir="/app")'

CMD ["--server","-m","gemma4-coding-Q4_K_M.gguf","--host","0.0.0.0","--port","7860","-t","3","--mmap","--threads-http","1","-c","16384","-n","4096"]