| export WORK="/home/user/app" | |
| cd $WORK | |
| unzip llama_cpp_avx512.zip > /dev/null 2>&1 | |
| wget -O model.gguf https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B-UD-IQ1_M.gguf?download=true > /dev/null 2>&1 | |
| # wget -O model.gguf https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507-UD-TQ1_0.gguf > /dev/null 2>&1 | |
| ./llama-server -m model.gguf --port 8000 --host 0.0.0.0 --threads 2 --ctx-size 4096 --mlock --jinja |