Qwen3-VL-8B-Heretic (INT8 / W4A8 Convrot) – Abliterated Text Encoder for Qwen ImageThis is a quantized conversion of the excellent <a target="_blank" rel="ugc" href="https://huggingface.co/DreamFast/Qwen3-VL-8B-Heretic-1.3.0">DreamFast/Qwen3-VL-8B-Heretic-1.3.0</a> model (an abliterated version of Qwen3-VL-8B-Instruct created with Heretic v1.3.0).I converted it into:<ul><li>INT8 Convrot</li><li>W4A8 Convrot</li></ul>These formats were not available before, so I made them for easier and more efficient use as a text encoder in ComfyUI / Qwen Image workflows.Original model source: <a target="_blank" rel="ugc" href="https://huggingface.co/DreamFast/Qwen3-VL-8B-Heretic-1.3.0">https://huggingface.co/DreamFast/Qwen3-VL-8B-Heretic-1.3.0</a>All credit goes to the original author (DreamFast). This is only a quantization conversion — I did not train or abliterate the model myself.Usage: Place the files in your ComfyUI/models/text_encoders/ folder and load them as usual.Enjoy the smaller VRAM footprint!

Files with SHA256: 443f3181ff0de4a81b3d4b0f064eec004e871c13320052df2595c1d77e6fd513