DuoNeural/Gemma-4-E4B-Claude-Abliterated-GGUF
Quantization (fewer layers) vs arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled. DuoNeural/Gemma-4-E4B-Claude-Abliterated-GGUF matches part of arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled (677 of its 2130 tensors; the rest of arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled has no counterpart). On the shared part: DuoNeural/Gemma-4-E4B-Claude-Abliterated-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 297 tensors match exactly and 380 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168