shafire/Zero-Gemma4-E4B-OpenZero-GGUF
Full fine-tune (fewer layers) vs unsloth/gemma-4-E4B-it. shafire/Zero-Gemma4-E4B-OpenZero-GGUF matches part of unsloth/gemma-4-E4B-it (677 of its 2130 tensors; the rest of unsloth/gemma-4-E4B-it has no counterpart). On the shared part: shafire/Zero-Gemma4-E4B-OpenZero-GGUF is a GGUF (Q5_K/F16) of different weights. Fine-tune: 99% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 2/2, Norms 0/296, MLP 126/126, other 0/85, Attention 168/168