DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING
LoRA-style vs trohrbaugh/Qwen3.5-9B-heretic-v2. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/215, Attention 152/332, MLP 96/208
7 derivatives checked
- DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF: Same weights, converted
- mradermacher/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-i1-GGUF: Quantization
- mradermacher/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-GGUF: Same weights, converted
- kryp1234/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF: Same weights, converted
- grizzfu/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF: Same weights, converted
- mmp2055/Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q4_K_S-imat-bughunter: Quantization
- mmp2055/qwen3.5-9b-claude-4.6-os-av-h-uncensored-think-d_au-imat-bughunter-v6: Quantization
3 other repos hold byte-for-byte identical weight files.