tiny sd needs about 1.4 GB of memory at Q4_K (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.8 GB (Q4_K) to 0.9 GB (Q8_0).
Tiny SD – a lightweight 0.53B parameter diffusion model
Tiny SD is a 0.53 billion parameter diffusion model released under the apache-2.0 license. It is available in two GGUF quantizations, Q4_K and Q8_0, and can be run directly with stable‑diffusion.cpp.
Good at
- Fast inference on modest hardware
- Low memory footprint
- Stable‑diffusion.cpp compatibility
Limits
- No vision support beyond diffusion
- Small context window not specified
- License requires compliance with apache-2.0
Best for
- Rapid prototyping of image generation
- Low‑budget inference on GPUs
- Educational demos
Who it’s for. Developers and hobbyists seeking a small, open‑source diffusion model that runs efficiently on limited GPU resources. The model is suitable for projects that require quick iteration and minimal memory usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q8_0 | 0.9 GB | 1.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (file size 0.77 GB, estimated memory 1.4 GB at 8k context). If more VRAM is available, Q8_0 (0.85 GB, 1.5 GB) offers higher precision.
What GPU do you need for tiny sd?
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 Q8_0 (0.9 GB file, about 1.5 GB in use).
Which tiny sd quant should you choose?
Q4_K (0.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about tiny sd
How much VRAM does tiny sd need?
About 1.4 GB at Q4_K with an 8K context window. That is the 0.8 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 tiny sd on an 8 GB GPU?
Yes, with Q8_0: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of tiny sd GGUF?
It depends on the quant: Q4_K is 0.8 GB, Q8_0 is 0.9 GB.
Where can I download tiny sd GGUF?
The files are on Hugging Face in the turingevo/tiny-sd-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 tiny sd use?
Hugging Face lists the license as apache-2.0. 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 Tiny SD on 8 GB VRAM?
Yes, the Q4_K quantization requires approximately 1.4 GB of VRAM at 8k context, which fits within an 8 GB GPU.
Does Tiny SD support vision tasks?
No, Tiny SD is a diffusion model and does not provide vision capabilities beyond image generation.