GGUF quants of Phi-4 using llama.cpp's [PR 10817](https://github.com/ggerganov/llama.cpp/pull/10817/commits/7555ab1cdcf873a6ba1dbba6a8e80fd653ad8052) from fairydreaming


See [matteogeniaccio](https://huggingface.co./matteogeniaccio/phi-4/tree/main) as well