BrainboxAI/law-il-E2B
Quantization (fewer layers) vs unsloth/gemma-4-E2B-it. BrainboxAI/law-il-E2B matches part of unsloth/gemma-4-E2B-it (565 of its 2011 tensors; the rest of unsloth/gemma-4-E2B-it has no counterpart). On the shared part: BrainboxAI/law-il-E2B is a GGUF quantization (Q4_K_M) of the same weights: 248 tensors match exactly and 317 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/247, MLP 0/105, other 0/71, Attention 0/140