SD3-5_large-Q4_0-gguf-4Bit

Accuracy vs. Size Tradeoff

Every variant is benchmarked against the FP16 baseline. Choose the right balance of accuracy and footprint for your workflow.

Usage Code Snippets

Which variant for your hardware?

Choose the right quantization path for your device and performance target.

About This Model

Stable Diffusion 3.5 Large is an advanced open-weight text-to-image model developed by Stability AI. Built upon the Multimodal Diffusion Transformer (MMDiT) architecture, the model contains approximately 8 billion parameters and delivers substantial improvements in image quality, prompt understanding, composition, typography, and human anatomy compared to previous Stable Diffusion generations. SD3.5 Large supports photorealistic rendering, digital art creation, concept design, marketing assets, product visualization, and professional content generation workflows. The GGUF quantized version enables efficient local deployment with significantly reduced memory requirements while preserving most of the original image quality. It is widely supported across ComfyUI, Forge, SwarmUI, and other local AI image generation platforms.