Mungert/gemma-3-27b-it-qat-q4_0-GGUF
Full fine-tune (fewer layers) vs google/gemma-3-27b-it. Mungert/gemma-3-27b-it-qat-q4_0-GGUF matches part of google/gemma-3-27b-it (807 of its 1247 tensors; the rest of google/gemma-3-27b-it has no counterpart). On the shared part: Mungert/gemma-3-27b-it-qat-q4_0-GGUF is a GGUF (Q3_K_M) of different weights. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Norms 336/373, MLP 186/186, Attention 248/248