jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker
Quantization (fewer layers) vs DavidAU/gemma-4-E4B-it-The-DECKARD-Claude-Opus-Expresso-Universe-HERETIC-UNCENSORED-Thinking. jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker matches part of DavidAU/gemma-4-E4B-it-The-DECKARD-Claude-Opus-Expresso-Universe-HERETIC-UNCENSORED-Thinking (677 of its 2130 tensors; the rest of DavidAU/gemma-4-E4B-it-The-DECKARD-Claude-Opus-Expresso-Universe-HERETIC-UNCENSORED-Thinking has no counterpart). On the shared part: jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker is a GGUF quantization (Q6_K/IQ4_NL) of the same weights: 297 tensors match exactly and 380 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168