minas2025/Gemma-4-E2B-Conversational-Uncensored
Quantization (fewer layers) vs llmfan46/gemma-4-E2B-it-ultra-uncensored-heretic. minas2025/Gemma-4-E2B-Conversational-Uncensored matches part of llmfan46/gemma-4-E2B-it-ultra-uncensored-heretic (565 of its 2011 tensors; the rest of llmfan46/gemma-4-E2B-it-ultra-uncensored-heretic has no counterpart). On the shared part: minas2025/Gemma-4-E2B-Conversational-Uncensored is a GGUF quantization (Q8) of the same weights: 247 tensors match exactly and 318 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/247, MLP 0/105, other 0/71, Attention 0/140