mradermacher/gemma-4-E4B-it-qat-q4_0-unquantized-heretic-GGUF
Same weights, converted (fewer layers) vs coder3101/gemma-4-E4B-it-qat-q4_0-unquantized-heretic. mradermacher/gemma-4-E4B-it-qat-q4_0-unquantized-heretic-GGUF matches part of coder3101/gemma-4-E4B-it-qat-q4_0-unquantized-heretic (623 of its 2076 tensors; the rest of coder3101/gemma-4-E4B-it-qat-q4_0-unquantized-heretic 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 0/278, MLP 0/126, other 0/85, Attention 0/132