mradermacher/gemma-4-E4B-it-heretic-v1-GGUF

Same weights, converted (fewer layers) vs MiguelMendez101/gemma-4-E4B-it-heretic-v1. mradermacher/gemma-4-E4B-it-heretic-v1-GGUF matches part of MiguelMendez101/gemma-4-E4B-it-heretic-v1 (677 of its 2130 tensors; the rest of MiguelMendez101/gemma-4-E4B-it-heretic-v1 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168

On the Hub · Downloads on Model Pulse