Originally Posted on: https://huggingface.co/Bedovyy/Qwen-Image-Edit-2511-NVFP4

Vae: https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae

Text Encoder: https://civitai.red/models/1864281/qwen-image?modelVersionId=2110105

(Text Encoder, qwen_2.5_vl_7b_fp8_scaled)

Qwen-Image-Edit-2511-NVFP4 | Optimized for NVIDIA RTX 50-Series (Blackwell)

Model Description:

This isn't just a standard version; this model has been processed using NVFP4 (NVIDIA Floating Point 4) quantization. This format is precision-engineered to extract every bit of power from the Blackwell architecture (NVIDIA 50-series). If you are running an RTX 50-series card, get ready for unprecedented inference speeds and incredibly efficient VRAM management.

Software Compatibility: This model is tested and ready to be integrated into the most advanced ecosystems in the AI community:

• 🚀 Forge Neo: Optimized performance and instant loading.

• 🧩 ComfyUI: Perfect for nodes supporting modern NVIDIA quantizations (ensure your nodes are up to date).

Credits: This model is a conversion based on the original work by Bedovyy on Hugging Face. I’ve brought it to Civitai to ensure that early adopters of next-gen hardware have immediate access to the most optimized tools available.