add Qwen-Image quantized version in the gallery #6323
Description
LocalAI version:
3.5.4 with docker image localai/localai:latest-gpu-nvidia-cuda-12
Environment, CPU architecture, OS, and Version:
Linux 6.11.0-25-generic #25-Ubuntu SMP PREEMPT_DYNAMIC x86_64 GNU/Linux
RTX 5090
Describe the bug
Qwen-image generation need too much VRAM event for a RTX 5090.
Can you add quantized version of this model in the gallery
To Reproduce
Expected behavior
Logs
Additional context
https://huggingface.co/city96/Qwen-Image-gguf/tree/main