DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
LoRA-style vs trohrbaugh/Qwen3.6-27B-heretic-ara. 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 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/319, Attention 304/556, MLP 192/304
11 derivatives checked
- DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
- mlx-community/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-OptiQ-4bit: Quantization
- BugTraceAI/BugTraceAI-CORE-Ultra-27B-Q6: Quantization
- BugTraceAI/BugTraceAI-CORE-Ultra-27B-Q4: Quantization
- ryryryan/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
- pupsipups/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
- pablo85318/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
- bernquant/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
- AndreyCodes/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
- Gr8white925/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
- Kasume412/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF: Quantization
4 other repos hold byte-for-byte identical weight files.