stable diffusion xl 1.0 turbo needs about 5.1 GB of memory at Q4_1 (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 3.9 GB (Q4_0) to 6.9 GB.
Stable Diffusion XL 1.0 Turbo – fast text‑to‑image generation
SDXL‑Turbo is a distilled version of SDXL 1.0, trained for real‑time synthesis. It can generate photorealistic images from a text prompt in a single network evaluation. The model is available in GGUF format and supports experimental use with gpustack/llama‑box.
Good at
- Single‑step image generation
- Fast inference
- High image fidelity
Limits
- Experimental support only with gpustack/llama‑box v0.0.75+
- No vision or audio capabilities
- License requires review for commercial use
Best for
- Real‑time art creation
- Rapid prototyping of image concepts
- Low‑latency image generation in applications
Who it’s for. Developers and researchers who need quick, high‑quality text‑to‑image generation. Suitable for prototyping, creative tools, and low‑latency inference scenarios.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q4_1 | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q8_0 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| — | 6.9 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_0 quant (file size 3.94 GB, estimated memory 4.9 GB). For 12 GB VRAM, Q4_1 (4.08 GB, 5.1 GB) or Q8_0 (5.04 GB, 6.1 GB) are suitable. Larger models require more memory.
What GPU do you need for stable diffusion xl 1.0 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 Q4_1 (4.1 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (6.9 GB file, about 8.3 GB in use).
Which stable diffusion xl 1.0 turbo quant should you choose?
Q4_1 (4.1 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 3.9 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
Frequently asked questions about stable diffusion xl 1.0 turbo
How much VRAM does stable diffusion xl 1.0 turbo need?
About 5.1 GB at Q4_1 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 stable diffusion xl 1.0 turbo on an 8 GB GPU?
Yes, with Q8_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of stable diffusion xl 1.0 turbo GGUF?
It depends on the quant: Q4_0 is 3.9 GB, Q4_1 is 4.1 GB, Q8_0 is 5.0 GB, file is 6.9 GB.
Where can I download stable diffusion xl 1.0 turbo GGUF?
The files are on Hugging Face in the gpustack/stable-diffusion-xl-1.0-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 stable diffusion xl 1.0 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?
Yes, the Q4_0 quant uses about 4.9 GB of VRAM at 8k context, fitting within an 8 GB GPU.
Is SDXL‑Turbo suitable for commercial projects?
Commercial use requires reviewing Stability AI’s license at https://stability.ai/license.
What software is needed to run this model?
It requires gpustack/llama‑box v0.0.75+ and the stable‑diffusion.cpp implementation patched by llama‑box.