>UniPic2-Metaquery-9B is an unified multimodal model built on Qwen2.5-VL-Instruct and SD3.5-Medium. It delivers end-to-end image understanding, text-to-image (T2I) generation, and image editing. Requires approximately 40 GB VRAM. For NVIDIA RTX 40-series GPUs, we recommend using the Skywork/UniPic2-Metaquery-Flash
https://huggingface.co/Skywork/UniPic2-Metaquery-9B
https://github.com/SkyworkAI/UniPic
I assume Q8/6 fits into 24GB