cstr/confucius4-tts-GGUF
Not comparable yet vs netease-youdao/Confucius4-TTS. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 378/667 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs netease-youdao/Confucius4-TTS. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 378/667 match), usually an architecture llama.cpp's name map doesn't cover yet.