cstr/confucius4-r2t2-GGUF
Not comparable yet vs netease-youdao/Confucius4-R2T2. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (317 of 707/710 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs netease-youdao/Confucius4-R2T2. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (317 of 707/710 match), usually an architecture llama.cpp's name map doesn't cover yet.