GGUF model commit (made with llama.cpp commit 9912b9e)

Add q6_K and q8_0 as split files due to 50GB limit

Initial GGUF model commit

Initial GGUF model commit

Initial GGUF model commit

Initial GGUF model commit

Initial GGUF model commit

Initial GGUF model commit

Initial GGUF model commit

Initial GGUF model commit

initial commit