Dockerfile

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

RUN apt update && apt install wget -y

RUN wget "https://huggingface.co/unsloth/Qwen3-4B-GGUF/resolve/main/Qwen3-4B-IQ4_NL.gguf" -O /model.gguf

CMD ["--server", "-m", "/model.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512", "--no-warmup"]