DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
Partial fine-tune vs DavidAU/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking. Partial change: 89% of the weights changed (attention, mlp, norms), in 64 of 64 layers.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 130/319, Attention 394/556, MLP 192/304
8 derivatives checked
- mradermacher/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-i1-GGUF: Quantization
- mradermacher/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-GGUF: Quantization
- zecanard/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-4bit-nvfp4: Quantization
- zecanard/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-int2-affine: Quantization
- TheCluster/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-mxfp4: Quantization
- zecanard/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-5bit-int5-affine: Quantization
- TheCluster/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-mxfp8: Quantization
- nightmedia/Qwen3.5-40B-Holodeck-Claude-Deckard-Picard-Heretic: Full fine-tune
4 other repos hold byte-for-byte identical weight files.