stable diffusion xl base 1.0 needs about 3.6 GB of memory at Q4_K (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.7 GB (Q4_0) to 6.9 GB (BF16).
Stable Diffusion XL 1.0 base model in GGUF format
Stable Diffusion XL 1.0 base is a latent diffusion model for text‑to‑image generation. It contains 3.47 billion parameters and is available in several GGUF quantizations. The model is licensed under CreativeML Open RAIL++-M.
Good at
- Text‑to‑image generation
- High‑resolution image creation
- Latent diffusion workflow
Limits
- Requires VAE on CPU; VAE consumes up to 10 GB VRAM
- No vision support in the base model
- License is CreativeML Open RAIL++-M
Best for
- Generating 1024×1024 images
- Creating images from text prompts
- Fine‑tuning on custom datasets
Who it’s for. This model is suited for developers and researchers who need a high‑quality text‑to‑image diffusion model in GGUF format. It works with stable‑diffusion.cpp and requires a CUDA‑capable GPU and CPU for VAE decoding.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 2.7 GB | 3.5 GB | Fits | Get file → | |
| Q4_K | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 4.2 GB | 5.2 GB | Fits | Get file → | |
| BF16 | 6.9 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM use Q4_0 (file size 2.71 GB, estimated 3.5 GB memory). For 12 GB VRAM use Q4_K (2.8 GB, 3.6 GB memory). For 16 GB VRAM use Q8_0 (4.18 GB, 5.2 GB memory). BF16 requires 6.94 GB file size and 8.3 GB memory.
What GPU do you need for stable diffusion xl base 1.0?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.9 GB file, about 8.3 GB in use).
Which stable diffusion xl base 1.0 quant should you choose?
Q4_K (2.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_0 at 2.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about stable diffusion xl base 1.0
How much VRAM does stable diffusion xl base 1.0 need?
About 3.6 GB at Q4_K with an 8K context window. That is the 2.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run stable diffusion xl base 1.0 on an 8 GB GPU?
Yes, with Q8_0: the 4.2 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of stable diffusion xl base 1.0 GGUF?
It depends on the quant: Q4_0 is 2.7 GB, Q4_K is 2.8 GB, Q8_0 is 4.2 GB, BF16 is 6.9 GB.
Where can I download stable diffusion xl base 1.0 GGUF?
The files are on Hugging Face in the kostakoff/stable-diffusion-xl-base-1.0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does stable diffusion xl base 1.0 use?
Hugging Face lists the license as openrail++. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 3.5 GB of VRAM at 8k context, which fits in 8 GB.
Does the model support image editing?
The base model can be used for image editing via SDEdit, but a separate refinement model is recommended for best results.
What license does this model use?
It is released under the CreativeML Open RAIL++-M license.