mradermacher/Gemma-4-31B-StyleTune-heretic-ara-i1-GGUF
Quantization (fewer layers) vs densenet/Gemma-4-31B-StyleTune-heretic-ara. mradermacher/Gemma-4-31B-StyleTune-heretic-ara-i1-GGUF matches part of densenet/Gemma-4-31B-StyleTune-heretic-ara (773 of its 1189 tensors; the rest of densenet/Gemma-4-31B-StyleTune-heretic-ara has no counterpart). On the shared part: mradermacher/Gemma-4-31B-StyleTune-heretic-ara-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 361 tensors match exactly and 412 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230