trohrbaugh/gemma-4-31b-it-heretic-ara
11 derivatives checked
- alonsoko/gemma-4-31b-it-abliterated-heretic-AWQ-W4A16: Quantization
- mradermacher/gemma-4-31b-it-heretic-ara-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-4-31b-it-heretic-ara-GGUF: Quantization (fewer layers)
- jfiekdjdk/gemma-4-31b-it-heretic-ara-gguf: Quantization (fewer layers)
- CCSSNE/gemma-4-31b-it-heretic-ara-gguf: Quantization (fewer layers)
- hell0ks/gemma-4-31b-it-heretic-ara-FP8: Quantization
- zecanard/gemma-4-31b-it-uncensored-heretic-ara-MLX-8bit-int8-affine: Quantization
- zecanard/gemma-4-31b-it-uncensored-heretic-ara-MLX-4bit-mixed_4_6: Quantization
- MRockatansky/Gemma-4-31B-storymaxxed2: LoRA-style
- MRockatansky/Gemma-4-31B-storymaxxed: LoRA-style
- MRockatansky/Gemma-4-31b-nomDePlume: LoRA-style
2 other repos hold byte-for-byte identical weight files.