tensorblock/soob3123_amoral-gemma3-12B-v2-GGUF
Quantization (fewer layers) vs soob3123/amoral-gemma3-12B-v2. tensorblock/soob3123_amoral-gemma3-12B-v2-GGUF matches part of soob3123/amoral-gemma3-12B-v2 (625 of its 1065 tensors; the rest of soob3123/amoral-gemma3-12B-v2 has no counterpart). On the shared part: tensorblock/soob3123_amoral-gemma3-12B-v2-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 289 tensors match exactly and 336 within quantization error.
Tensors changed: Norms 0/289, MLP 0/144, Attention 0/192