mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-fp16
Same weights, repacked (fewer layers) vs OBLITERATUS/gemma-4-E4B-it-OBLITERATED. mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-fp16 matches part of OBLITERATUS/gemma-4-E4B-it-OBLITERATED (719 of its 2130 tensors; the rest of OBLITERATUS/gemma-4-E4B-it-OBLITERATED has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/2, Norms 0/296, other 0/127, MLP 0/126, Attention 0/168