huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated
Abliterated vs Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 40 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 337/1165, lm_head 0/1, Embeddings 0/5, Attention 41/392, other 0/1, Norms 0/247
8 derivatives checked
- cesarsal1nas/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-Q4_K_M-GGUF: Quantization
- mradermacher/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-i1-GGUF: Quantization
- mradermacher/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-GGUF: Quantization
- lhca521/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-GGUF: Quantization
- tstepspam/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-Q8-MLX: Quantization
- tstepspam/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-Q4-MLX: Quantization
- YuYu1015/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-int4-AutoRound: Quantization
- elbelga/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated_MXFP4_MOE: Same weights, converted