$ ~/llama.cpp/build/bin/llama-server --list-devices
Available devices:
  CUDA0: NVIDIA GeForce GTX 1650 Ti with Max-Q Design (3732 MiB, 3671 MiB free)

$ CUDA_VISIBLE_DEVICES= ~/llama.cpp/build-cpu/bin/llama-server --list-devices
Available devices:
  (none)