Stable Diffusion XL 1.0
The practical default for 1024px work on consumer GPUs. Two text encoders, both small.
What you actually download
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.
| Precision | Everything in VRAM | Text encoder on CPU | Sequential CPU offload |
|---|---|---|---|
| BF16 / FP16Reference quality. What the repos ship by default. | 9.2 GB | 7.6 GB | 7.4 GB |
| FP8Roughly half the weight memory. Small quality cost, widely used for Flux and SD 3.5. | 5.8 GB | 5.0 GB | 4.8 GB |
| NF4 / INT4Aggressive 4-bit. Visible quality loss, but it puts big models on small cards. | 4.8 GB | 4.0 GB | 3.8 GB |
Which machines can run it
75 of the 75 devices we profile can run Stable Diffusion XL 1.0 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.
Licence: OpenRAIL++
With conditions. Stable Diffusion XL 1.0 is released under OpenRAIL++. Commercial use is permitted, but the terms carry use restrictions that travel with the model — read them before shipping.
Compare model licences →Stable Diffusion XL 1.0: common questions
- How much VRAM does Stable Diffusion XL 1.0 need?
- At 1024x1024 and batch 1, Stable Diffusion XL 1.0 peaks at about 9.2GB with everything resident at BF16, and as little as 3.8GB at NF4 + sequential CPU offload. The weights alone are 6.9GB at BF16 — 5.1GB of transformer, 1.6GB of text encoder and 0.17GB of VAE.
- Which GPUs can run Stable Diffusion XL 1.0?
- 75 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 9.2GB. Lower precision and text-encoder offload widen that list considerably.
- Can Stable Diffusion XL 1.0 be used commercially?
- With conditions. Stable Diffusion XL 1.0 is released under OpenRAIL++. 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 XL 1.0?
- Not much. Stable Diffusion XL 1.0 uses small text encoders totalling just 1.64GB, so offloading them frees very little — peak VRAM at BF16 only drops from 9.2GB to 7.6GB. Lowering precision is the more effective lever here.
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.
Other open image models
Guides that go deeper
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