metaltiger775/gemma-4-E4B-it-OBLITERATED-gguf
Partial fine-tune (fewer layers) vs google/gemma-4-E4B-it. metaltiger775/gemma-4-E4B-it-OBLITERATED-gguf matches part of google/gemma-4-E4B-it (623 of its 2130 tensors; the rest of google/gemma-4-E4B-it has no counterpart). On the shared part: metaltiger775/gemma-4-E4B-it-OBLITERATED-gguf is a GGUF (F16) of different weights. Partial change: 39% of the weights changed (attention, embeddings, mlp), in 24 of 42 layers.
Tensors changed: Embeddings 1/2, Norms 0/278, MLP 72/126, other 0/85, Attention 62/132