Qwen3-chat-speed / Dockerfile
Boning c
Update Dockerfile
33574a0 verified
raw
history blame contribute delete
337 Bytes
FROM ghcr.io/ggml-org/llama.cpp:full
RUN apt update && apt install wget -y
RUN wget "https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF/resolve/main/Qwen3-30B-A3B-UD-Q8_K_XL.gguf" -O /Qwen3-30B-A3B-UD-Q8_K_XL.gguf
CMD ["--server", "-m", "/Qwen3-30B-A3B-UD-Q8_K_XL.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512", "--no-warmup"]