| export WORK="/home/user/app" | |
| cd $WORK | |
| unzip llama_cpp_avx512.zip > /dev/null 2>&1 | |
| echo "✅ Booting up llama server..." | |
| # wget -O model.gguf https://huggingface.co/lmstudio-community/Qwen3-4B-Instruct-2507-GGUF/resolve/main/Qwen3-4B-Instruct-2507-Q6_K.gguf?download=true > /dev/null 2>&1 | |
| wget -O model.gguf https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main/gpt-oss-20b-F16.gguf?download=true > /dev/null 2>&1 | |
| ./llama-server -m model.gguf --port 8000 --host 0.0.0.0 --threads 2 --ctx-size 4096 --mlock --jinja | |
| echo "✅ llama server running on port 8000" |