google/gemma-3-4b-it-qat-q4_0-gguf
Full fine-tune (fewer layers) vs google/gemma-3-4b-it. google/gemma-3-4b-it-qat-q4_0-gguf matches part of google/gemma-3-4b-it (443 of its 883 tensors; the rest of google/gemma-3-4b-it has no counterpart). On the shared part: google/gemma-3-4b-it-qat-q4_0-gguf is a GGUF (Q4_0) of different weights. Fine-tune: 100% of the weights changed, across 34 of 34 layers.
Tensors changed: Norms 179/205, MLP 102/102, Attention 136/136
1 derivatives checked
- stduhpf/google-gemma-3-4b-it-qat-q4_0-gguf-small: Quantization