s1arsky/Gemma-4-31B-Cognitive-Unshackled-Q4_KS_GGUF
Quantization (fewer layers) vs aifeifei798/Gemma-4-31B-Cognitive-Unshackled. s1arsky/Gemma-4-31B-Cognitive-Unshackled-Q4_KS_GGUF matches part of aifeifei798/Gemma-4-31B-Cognitive-Unshackled (772 of its 1188 tensors; the rest of aifeifei798/Gemma-4-31B-Cognitive-Unshackled has no counterpart). On the shared part: s1arsky/Gemma-4-31B-Cognitive-Unshackled-Q4_KS_GGUF is a GGUF quantization (Q4_K_S) 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