mradermacher/gemma-4-E2B-it-heretic-ara-GGUF
Same weights, converted (fewer layers) vs p-e-w/gemma-4-E2B-it-heretic-ara. mradermacher/gemma-4-E2B-it-heretic-ara-GGUF matches part of p-e-w/gemma-4-E2B-it-heretic-ara (565 of its 2011 tensors; the rest of p-e-w/gemma-4-E2B-it-heretic-ara has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 36 new tensors.
Tensors changed: Embeddings 0/2, Norms 0/247, MLP 0/105, other 0/71, Attention 0/140