lmstudio-community/gemma-3n-E2B-it-MLX-bf16
Different architecture vs google/gemma-3n-E2B-it. Different architecture: only 530 of 1556/1556 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.
Different architecture vs google/gemma-3n-E2B-it. Different architecture: only 530 of 1556/1556 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.