mradermacher/copywriter-gemma4-31b-GGUF
Quantization (fewer layers) vs akwin123/copywriter-gemma4-31b. mradermacher/copywriter-gemma4-31b-GGUF matches part of akwin123/copywriter-gemma4-31b (772 of its 1188 tensors; the rest of akwin123/copywriter-gemma4-31b has no counterpart). On the shared part: mradermacher/copywriter-gemma4-31b-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