sdxl turbo needs about 5.1 GB of memory at Q8_0 (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU.
Fast, photorealistic text-to-image generation in a single network evaluation
SDXL‑Turbo is a distilled version of SDXL 1.0, trained for real‑time synthesis. It uses Adversarial Diffusion Distillation to produce high‑quality images in 1–4 sampling steps. The model is available in a single GGUF file quantized to Q8_0.
Good at
- Real‑time image synthesis
- High image fidelity with few steps
- Single‑network evaluation
Limits
- Requires 5.1 GB VRAM at 8k context (approx.)
- Only Q8_0 quant available
- No vision or audio capabilities
Best for
- Rapid prototyping of text‑to‑image pipelines
- Low‑latency image generation in applications
- Research on real‑time diffusion models
Who it’s for. Developers and researchers needing fast, high‑quality image generation. The model supports both non‑commercial and commercial use under the provided license. It is suitable for research on generative models, real‑time applications, and safe deployment studies.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 4.1 GB | 5.1 GB | Fits | Get file → |
The only available quant is Q8_0, with a file size of 4.1 GB and an estimated VRAM usage of 5.1 GB at 8k context. This is the recommended version for any deployment. No other quants are listed, so memory estimates are approximate based on this file.
What GPU do you need for sdxl turbo?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
Which sdxl turbo quant should you choose?
Q8_0 (4.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about sdxl turbo
How much VRAM does sdxl turbo need?
About 5.1 GB at Q8_0 with an 8K context window. That is the 4.1 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 sdxl turbo on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sdxl turbo GGUF?
It depends on the quant: Q8_0 is 4.1 GB.
Where can I download sdxl turbo GGUF?
The files are on Hugging Face in the OlegSkutte/sdxl-turbo-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 sdxl turbo use?
Hugging Face lists the license as other. 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 SDXL‑Turbo on 8 GB VRAM?
The Q8_0 quant requires approximately 5.1 GB VRAM at 8k context, so it can run on 8 GB VRAM with room for overhead.
Is SDXL‑Turbo suitable for commercial use?
Yes, the model is available for commercial use under the Stability AI license. Refer to the license link for details.
Does SDXL‑Turbo support vision or audio input?
No, SDXL‑Turbo is a text‑to‑image model and does not support vision or audio input.