mradermacher/Gemma4-E4B-TIES-3mask-r64-GGUF
Same weights, converted (fewer layers) vs ToastyPigeon/Gemma4-E4B-TIES-3mask-r64. mradermacher/Gemma4-E4B-TIES-3mask-r64-GGUF matches part of ToastyPigeon/Gemma4-E4B-TIES-3mask-r64 (623 of its 2076 tensors; the rest of ToastyPigeon/Gemma4-E4B-TIES-3mask-r64 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