Dzluck/gemma-4-E4B-Gemini-3.1-Pro-Reasoning-Distill-GGUF
Quantization (fewer layers) vs Ayodele01/gemma-4-E4B-Gemini-3.1-Pro-Reasoning-Distill. Dzluck/gemma-4-E4B-Gemini-3.1-Pro-Reasoning-Distill-GGUF matches part of Ayodele01/gemma-4-E4B-Gemini-3.1-Pro-Reasoning-Distill (677 of its 2130 tensors; the rest of Ayodele01/gemma-4-E4B-Gemini-3.1-Pro-Reasoning-Distill has no counterpart). On the shared part: Dzluck/gemma-4-E4B-Gemini-3.1-Pro-Reasoning-Distill-GGUF is a GGUF quantization (Q8_0) 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