mradermacher/gemma-3-4b-it-heretic-uncensored-abliterated-balanced-GGUF
Same weights, converted (fewer layers) vs DavidAU/gemma-3-4b-it-heretic-uncensored-abliterated-balanced. mradermacher/gemma-3-4b-it-heretic-uncensored-abliterated-balanced-GGUF matches part of DavidAU/gemma-3-4b-it-heretic-uncensored-abliterated-balanced (444 of its 883 tensors; the rest of DavidAU/gemma-3-4b-it-heretic-uncensored-abliterated-balanced has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136