mradermacher/Goetia-26B-A4B-v1.3-GGUF
Quantization vs OccultAI/Goetia-26B-A4B-v1.3. mradermacher/Goetia-26B-A4B-v1.3-GGUF is a GGUF quantization (Q8_0) of the same weights: 301 tensors match exactly and 206 within quantization error.
Tensors changed: Norms 0/271, MLP 0/90, other 0/30, Attention 0/115, Embeddings 0/1