OBLITERATUS/Gemma-4-12B-OBLITERATED
Partial fine-tune vs google/gemma-4-12B-it. Partial change: 48% of the weights changed (attention, embeddings, mlp), in 21 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 0/291, other 0/54, MLP 63/144, Attention 80/184
10 derivatives checked
- mradermacher/Gemma-4-12B-OBLITERATED-i1-GGUF: Quantization
- mradermacher/Gemma-4-12B-OBLITERATED-GGUF: Quantization
- deadbydawn101/ravenx-Gemma4-12B-MTP-OBLITERATED-OpenMAI-OpenMythos-deep-reasoning-mlx: LoRA-style
- deadbydawn101/RavenX-OpenFable-Coderagent-gemma-4-12B-coder-fable5-composer-Soulinfused-Remastered-GGUF: Full fine-tune
- wepiqx/gemma-4-12B-OBLITERATED-SHQ7-GGUF: Quantization
- bsisduck/Gemma-4-12B-OBLITERATED-MLX-BF16: Same weights, repacked
- deadbydawn101/RavenX-OpenFable-Coder-Gemma-4-12B-GGUF: Quantization
- TaQuants/Gemma-4-12B-OBLITERATED-TaQuants-GGUF: Quantization
- deadbydawn101/ravenx-Gemma4-12B-MTP-OBLITERATED-OpenMAI-OpenMythos-deep-reasoning-GGUF: LoRA-style
- nico248000000000/Gemma-4-12B-OBLITERATED-cyber: LoRA-style
22 other repos hold byte-for-byte identical weight files.