mradermacher/amoral-gemma3-12B-vision-GGUF
Quantization (fewer layers) vs gghfez/amoral-gemma3-12B-vision. mradermacher/amoral-gemma3-12B-vision-GGUF matches part of gghfez/amoral-gemma3-12B-vision (626 of its 1065 tensors; the rest of gghfez/amoral-gemma3-12B-vision has no counterpart). On the shared part: mradermacher/amoral-gemma3-12B-vision-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