Stable Diffusion 3.5 Large

A diffusion pipeline is three separate models. These sizes are read from the real .safetensors files in the Hugging Face repository, not estimated.

Peak VRAM at 1024×1024, one image

Every combination of precision and offload strategy. Lower precision costs image quality; offloading costs speed.

71 of the 75 devices we profile can run Stable Diffusion 3.5 Large at 1024×1024 in some configuration. Showing the best-quality setup each one supports.

Showing the 30 devices with the most memory. The full hardware matrix covers all 75.

With conditions. Stable Diffusion 3.5 Large is released under Stability Community License. Commercial use is permitted, but the terms carry use restrictions that travel with the model — read them before shipping.

Stable Diffusion 3.5 Large: common questions

How much VRAM does Stable Diffusion 3.5 Large need?

At 1024x1024 and batch 1, Stable Diffusion 3.5 Large peaks at about 30.6GB with everything resident at BF16, and as little as 7.8GB at NF4 + text encoder on CPU. The weights alone are 27.9GB at BF16 — 16.3GB of transformer, 11.4GB of text encoder and 0.17GB of VAE.

Which GPUs can run Stable Diffusion 3.5 Large?

71 of the 75 devices we profile can run it at 1024x1024 in some configuration. The Apple Mac Studio (M5 Ultra, 512GB, 2026) handles it best, at about 30.6GB. Lower precision and text-encoder offload widen that list considerably.

Can Stable Diffusion 3.5 Large be used commercially?

With conditions. Stable Diffusion 3.5 Large is released under Stability Community License. Commercial use is permitted, but the terms carry use restrictions that travel with the model — read them before shipping.

Does offloading the text encoder help on Stable Diffusion 3.5 Large?

Yes, substantially. Stable Diffusion 3.5 Large uses a large language model as its text encoder — 11.4GB at full precision. Encoding happens once per prompt, so moving it to CPU costs a couple of seconds and frees that 11.4GB for the rest of the run, taking peak VRAM at BF16 from 30.6GB down to 19.2GB.

Weight sizes read from the model repository on 2026-09-12. Activation memory is an approximation, not a benchmark — BFWR does not run a hardware test lab.

Which GPUs have the VRAM these models need, and what they cost right now.

• How to Run Stable Diffusion Locally: Hardware, VRAM and SetupCurrent models from SD 1.5 to Qwen-Image, and the VRAM each needs.Read the guide
• Stable Diffusion LoRA: Base Models, Weights and StackingMatching the base model, setting strength, and combining adapters.Read the guide
• How to Increase VRAM: What Actually Works on PC, Laptop and MacIt depends where the memory physically lives.Read the guide