qwen3-4b-cpu / Dockerfile
Nomos42's picture
init: CPU LLM Space template
9945200 verified
Raw
History Blame Contribute Delete
761 Bytes
# Nomos42 Qwen3-4B-Instruct CPU LLM Space — Docker SDK
FROM python:3.11-slim-bookworm
RUN apt-get update && apt-get install -y --no-install-recommends \
cmake build-essential git curl \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY app.py .
EXPOSE 7860
RUN useradd -m -u 1000 user
USER user
# Qwen3-4B-Instruct-2507 Q4_K_M (~2.5 GB) — top quality/size Apr 2026
# MMLU-Redux 83.1 | MMLU-Pro 61.4 | IFEval 69.5
ENV MODEL_REPO=unsloth/Qwen3-4B-Instruct-2507-GGUF \
MODEL_FILE=Qwen3-4B-Instruct-2507-Q4_K_M.gguf \
MODEL_DISPLAY=qwen3-4b-instruct \
CHAT_FORMAT=chatml \
N_CTX=2048 \
N_THREADS=2 \
HF_HOME=/tmp/hf-cache
CMD ["python", "app.py"]