mradermacher/Gemma4-31B-Finetuned-V2-GGUF
Quantization (fewer layers) vs SF-Foundation/Gemma4-31B-Finetuned-V2. mradermacher/Gemma4-31B-Finetuned-V2-GGUF matches part of SF-Foundation/Gemma4-31B-Finetuned-V2 (772 of its 1188 tensors; the rest of SF-Foundation/Gemma4-31B-Finetuned-V2 has no counterpart). On the shared part: mradermacher/Gemma4-31B-Finetuned-V2-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230