himalaya-ai/himalaya-gemma-4-e2b-it-gguf
Full fine-tune (fewer layers) vs google/gemma-4-E2B-it. himalaya-ai/himalaya-gemma-4-e2b-it-gguf matches part of google/gemma-4-E2B-it (565 of its 2011 tensors; the rest of google/gemma-4-E2B-it has no counterpart). On the shared part: himalaya-ai/himalaya-gemma-4-e2b-it-gguf is a GGUF (BF16) of different weights. Fine-tune: 100% of the weights changed, across 35 of 35 layers.
Tensors changed: Embeddings 2/2, Norms 97/247, MLP 105/105, other 71/71, Attention 140/140