(based on vicuna-tools/vicuna-installation-guide but using another LLAMA repo)
$ git clone https://github.com/ggerganov/llama.cpp.git$ cd llama.cpp$ make -j$ cd models$ wget -c https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized/resolve/main/ggml-vicuna-13B-1.1-q5_1.bin$ ./server -t 12 -m models/ggml-vicuna-13B-1.1-q5_1.bin