mradermacher/Caelum-G4-38B-A12.5B-GGUF
Quantization vs EryriLabs/Caelum-G4-38B-A12.5B. mradermacher/Caelum-G4-38B-A12.5B-GGUF is a GGUF quantization (Q8_0) of the same weights: 481 tensors match exactly and 329 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/433, Attention 0/184, MLP 0/144, other 0/48