nuofang/gemma4-e4b-mahou-nsfw-GGUF
Quantization (fewer layers) vs Pranavz/gemma4-e4b-mahou-nsfw. nuofang/gemma4-e4b-mahou-nsfw-GGUF matches part of Pranavz/gemma4-e4b-mahou-nsfw (623 of its 2076 tensors; the rest of Pranavz/gemma4-e4b-mahou-nsfw has no counterpart). On the shared part: nuofang/gemma4-e4b-mahou-nsfw-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 279 tensors match exactly and 344 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132