manojbillionaire123/gemma-4-E4B-it-qat-GGUF
Full fine-tune (fewer layers) vs google/gemma-4-E4B-it-qat-q4_0-unquantized. manojbillionaire123/gemma-4-E4B-it-qat-GGUF matches part of google/gemma-4-E4B-it-qat-q4_0-unquantized (623 of its 2076 tensors; the rest of google/gemma-4-E4B-it-qat-q4_0-unquantized has no counterpart). On the shared part: manojbillionaire123/gemma-4-E4B-it-qat-GGUF is a GGUF (Q2_K_XL) of different weights. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 2/2, Norms 209/278, MLP 126/126, other 85/85, Attention 132/132