[](https://hamel.dev/notes/llm/inference/inference.html#cb14-1)python3 download-model.py TheBloke/Llama-2-7B-GPTQ
[](https://hamel.dev/notes/llm/inference/inference.html#cb14-2)python3 server.py --listen --extensions openai --loader exllama_hf --model TheBloke_Llama-2-7B-GPTQ