mradermacher/gemma4-31b-jp-GGUF
Quantization (fewer layers) vs FinancialSupport/gemma4-31b-jp. mradermacher/gemma4-31b-jp-GGUF matches part of FinancialSupport/gemma4-31b-jp (772 of its 1188 tensors; the rest of FinancialSupport/gemma4-31b-jp has no counterpart). On the shared part: mradermacher/gemma4-31b-jp-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