mradermacher/Gemma-4-E4B-Abliterated-GGUF

Same weights, converted (fewer layers) vs DuoNeural/Gemma-4-E4B-Abliterated. mradermacher/Gemma-4-E4B-Abliterated-GGUF matches part of DuoNeural/Gemma-4-E4B-Abliterated (677 of its 2130 tensors; the rest of DuoNeural/Gemma-4-E4B-Abliterated 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