mradermacher/gemma-4-E4B-it-QAT-SOMPOA-heresy-GGUF
Same weights, converted (fewer layers) vs MuXodious/gemma-4-E4B-it-QAT-SOMPOA-heresy. mradermacher/gemma-4-E4B-it-QAT-SOMPOA-heresy-GGUF matches part of MuXodious/gemma-4-E4B-it-QAT-SOMPOA-heresy (623 of its 2076 tensors; the rest of MuXodious/gemma-4-E4B-it-QAT-SOMPOA-heresy 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