Originally Posted on: <a target="_blank" rel="ugc" href="https://huggingface.co/Hippotes/Qwen-Image-2512-nvfp4">https://huggingface.co/Hippotes/Qwen-Image-2512-nvfp4</a>Vae: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae">https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae</a>Text Encoder: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1864281/qwen-image?modelVersionId=2110105">https://civarchive.com/models/1864281/qwen-image?modelVersionId=2110105</a>(Text Encoder, <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">qwen_2.5_vl_7b_fp8_scaled)<h3 id="qwen-image-2512-nvfp4-or-optimized-for-nvidia-rtx-50-series-(blackwell)">Qwen-Image-2512-NVFP4 | Optimized for NVIDIA RTX 50-Series (Blackwell)</h3>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:<ul><li>🚀 Forge Neo: Optimized performance and instant loading.</li><li>🧩 ComfyUI: Perfect for nodes supporting modern NVIDIA quantizations (ensure your nodes are up to date).</li></ul>

Files with SHA256: e2f742e97f340c29088db6b06bf278e9f78dee581ac417999c24614ada7b1fb5