DavidAU/Qwen3-VL-32B-Gemini-Heretic-Uncensored-Thinking
LoRA-style vs coder3101/Qwen3-VL-32B-Thinking-heretic-v2. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/373, MLP 192/316, Attention 256/364, lm_head 0/1
3 derivatives checked
- mradermacher/Qwen3-VL-32B-Gemini-Heretic-Uncensored-Thinking-i1-GGUF: Quantization (fewer layers)
- mradermacher/Qwen3-VL-32B-Gemini-Heretic-Uncensored-Thinking-GGUF: Quantization (fewer layers)
- Merlinoz11/Qwen3-VL-32B-Gemini-Heretic-Uncensored-Thinking-Q8_0-GGUF: Quantization (fewer layers)
1 other repos hold byte-for-byte identical weight files.