sraivante/Housy-Gemma3-4B-Instruct-GGUF
Full fine-tune (fewer layers) vs unsloth/gemma-3-4b-it. sraivante/Housy-Gemma3-4B-Instruct-GGUF matches part of unsloth/gemma-3-4b-it (444 of its 883 tensors; the rest of unsloth/gemma-3-4b-it has no counterpart). On the shared part: sraivante/Housy-Gemma3-4B-Instruct-GGUF is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 34 of 34 layers.
Tensors changed: Embeddings 1/1, Norms 0/205, MLP 102/102, Attention 136/136