mradermacher/amoral-gemma3-12B-v1-GGUF
Quantization (fewer layers) vs Wutheringaadadadd/amoral-gemma3-12B-v1. mradermacher/amoral-gemma3-12B-v1-GGUF matches part of Wutheringaadadadd/amoral-gemma3-12B-v1 (626 of its 1065 tensors; the rest of Wutheringaadadadd/amoral-gemma3-12B-v1 has no counterpart). On the shared part: mradermacher/amoral-gemma3-12B-v1-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192