ermiaazarkhalili/Gemma4-E4B-SFT-Fable5-Glint-GGUF
Full fine-tune (fewer layers) vs unsloth/gemma-4-E4B-it. ermiaazarkhalili/Gemma4-E4B-SFT-Fable5-Glint-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: ermiaazarkhalili/Gemma4-E4B-SFT-Fable5-Glint-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 2/2, Norms 0/296, MLP 126/126, other 84/85, Attention 168/168