mradermacher/gemma-4-31b-unslop-good-lora-v2-full-GGUF
Quantization (fewer layers) vs Oysiyl/gemma-4-31b-unslop-good-lora-v2-full. mradermacher/gemma-4-31b-unslop-good-lora-v2-full-GGUF matches part of Oysiyl/gemma-4-31b-unslop-good-lora-v2-full (772 of its 1188 tensors; the rest of Oysiyl/gemma-4-31b-unslop-good-lora-v2-full has no counterpart). On the shared part: mradermacher/gemma-4-31b-unslop-good-lora-v2-full-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