Peter-A-P/smallprint-4b-gguf
Full fine-tune (fewer layers) vs google/gemma-4-E4B. Peter-A-P/smallprint-4b-gguf matches part of google/gemma-4-E4B (623 of its 2130 tensors; the rest of google/gemma-4-E4B has no counterpart). On the shared part: Peter-A-P/smallprint-4b-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 0/278, MLP 126/126, other 84/85, Attention 132/132