mradermacher/gemma-4-31B-it-noloop-GGUF
Quantization (fewer layers) vs edgerunner-ai/gemma-4-31B-it-noloop. mradermacher/gemma-4-31B-it-noloop-GGUF matches part of edgerunner-ai/gemma-4-31B-it-noloop (772 of its 1188 tensors; the rest of edgerunner-ai/gemma-4-31B-it-noloop has no counterpart). On the shared part: mradermacher/gemma-4-31B-it-noloop-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