Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.

Built with Qwen. Fine-tuned checkpoint published by abenzerps in abenzerps/Qwen-Image-2.1-Uncensored-GGUF, revision 40319fb15542f0ad22921e0124a191a8a935a60a. The author describes training and merging a LoRA; the recipe and training data have not been independently verified.

EliovpAI extracted the BF16 tensor bytes losslessly from qwen-image-2.1-UC-BF16.gguf and converted the transformer to the balanced Quark MXFP4 profile. Text/vision encoding reuses the verified balanced conversion of the original Qwen weights; the VAE retains BF16 inference precision. Original companion source: Qwen/Qwen-Image-2.1, revision 790c92633540aa0cb11d9abf19eb46d861714758.

Modified packed safetensors carry a conversion notice. Runtime modifications add architecture-based selection of the existing native decoder, checkpoint verification and the attributed model identity. No new fine-tuning was performed by EliovpAI for this release. Native runtime terms are provided in artifacts/NOTICE.