theroar/linguapal-e2b
Full fine-tune (fewer layers) vs google/gemma-4-E2B-it. theroar/linguapal-e2b matches part of google/gemma-4-E2B-it (505 of its 2011 tensors; the rest of google/gemma-4-E2B-it has no counterpart). On the shared part: theroar/linguapal-e2b is a GGUF (Q4_0/Q2_K) of different weights. Fine-tune: 100% of the weights changed, across 35 of 35 layers.
Tensors changed: Embeddings 2/2, Norms 177/227, MLP 105/105, other 71/71, Attention 100/100