WasamiKirua/Gemma-4-E4B-Samantha-GGUF
Quantization (fewer layers) vs llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic. WasamiKirua/Gemma-4-E4B-Samantha-GGUF matches part of llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic (677 of its 2130 tensors; the rest of llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic has no counterpart). On the shared part: WasamiKirua/Gemma-4-E4B-Samantha-GGUF is a GGUF quantization (Q8_0) of the same weights: 296 tensors match exactly and 381 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168