Initial deployment of Claude Code with Qwen local

Dockerfile

@@ -16,9 +16,9 @@ WORKDIR /app
 # Install llama-cpp-python with OpenBLAS and Streamlit
 RUN pip install llama-cpp-python[server] streamlit
 
-# Download Qwen2.5-Coder-7B-Instruct GGUF Q4_K_M
+# Download Qwen2.5-Coder-3B-Instruct GGUF Q4_K_M
 RUN mkdir -p /app/models
-RUN curl -L -o /app/models/qwen2.5-coder-7b-instruct-q4_k_m.gguf https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_k_m.gguf
+RUN curl -L -o /app/models/qwen2.5-coder-3b-instruct-q4_k_m.gguf https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF/resolve/main/qwen2.5-coder-3b-instruct-q4_k_m.gguf
 
 # Install Claude Code globally
 RUN npm install -g @anthropic-ai/claude-code
@@ -33,7 +33,7 @@ COPY app_claude_code_gui.py /app/app_claude_code_gui.py
 # Create a startup script
 RUN echo '#!/bin/bash\n\
 # Start llama-cpp-python server in background\n\
-python3 -m llama_cpp.server --model /app/models/qwen2.5-coder-7b-instruct-q4_k_m.gguf --host 0.0.0.0 --port 8001 &\n\
+python3 -m llama_cpp.server --model /app/models/qwen2.5-coder-3b-instruct-q4_k_m.gguf --host 0.0.0.0 --port 8001 &\n\
 \n\
 # Wait for server to start\n\
 until curl -s http://localhost:8001/v1/models > /dev/null; do\n\