InfinimindCreations/gemma-4-E4B-it-uncensored-vision
Quantization (fewer layers) vs InfinimindCreations/gemma-4-E4B-it-uncensored. InfinimindCreations/gemma-4-E4B-it-uncensored-vision matches part of InfinimindCreations/gemma-4-E4B-it-uncensored (677 of its 2130 tensors; the rest of InfinimindCreations/gemma-4-E4B-it-uncensored has no counterpart). On the shared part: InfinimindCreations/gemma-4-E4B-it-uncensored-vision 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