stable diffusion v1 5 needs about 2.3 GB of memory at Q5_1 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 1.6 GB (Q4_0) to 4.3 GB (F32).
Stable Diffusion v1‑5 – 1.07 B parameter latent text‑to‑image model
Stable Diffusion v1‑5 is a latent diffusion model that generates photo‑realistic images from text prompts. It is based on runwayml/stable‑diffusion‑v1‑5 and fine‑tuned on 595k steps. The model is available in GGUF format with multiple quantizations.
Good at
- Text‑to‑image generation
- High‑resolution image synthesis
- Latent diffusion workflow
Limits
- No vision support
- Requires 8 k context for full performance
- CreativeML OpenRAIL M license
Best for
- Creating artwork from prompts
- Editing images with text instructions
- Generating concept visuals
Who it’s for. Developers and artists who need a lightweight, quantized version of Stable Diffusion for local inference. The model is suitable for use with llama.cpp, ComfyUI, AUTOMATIC1111, and other compatible tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q5_0 | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q5_1 | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 2.5 GB | Fits | Get file → | |
| F16 | 2.1 GB | 2.9 GB | Fits | Get file → | |
| F32 | 4.3 GB | 5.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_1 (file size 1.57 GB, estimated 2.3 GB memory). If 12 GB VRAM is available, Q8_0 (1.76 GB, 2.5 GB memory) or F16 (2.13 GB, 2.9 GB memory) provide higher quality. F32 (4.27 GB, 5.3 GB memory) is best for maximum fidelity but needs more memory.
What GPU do you need for stable diffusion v1 5?
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 F16 (2.1 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (4.3 GB file, about 5.3 GB in use).
Which stable diffusion v1 5 quant should you choose?
Q5_1 (1.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_0 at 1.6 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 v1 5
How much VRAM does stable diffusion v1 5 need?
About 2.3 GB at Q5_1 with an 8K context window. That is the 1.6 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 v1 5 on an 8 GB GPU?
Yes, with F32: the 4.3 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of stable diffusion v1 5 GGUF?
It depends on the quant: Q4_0 is 1.6 GB, Q4_1 is 1.6 GB, Q5_0 is 1.6 GB, Q5_1 is 1.6 GB, Q8_0 is 1.8 GB, F16 is 2.1 GB and 1 more.
Where can I download stable diffusion v1 5 GGUF?
The files are on Hugging Face in the second-state/stable-diffusion-v1-5-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 v1 5 use?
Hugging Face lists the license as creativeml-openrail-m. 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 Stable Diffusion v1‑5 on 8 GB VRAM?
Yes, use the Q4_0 or Q4_1 quantization. Each requires about 2.3 GB of VRAM at 8 k context.
What license does this model use?
CreativeML OpenRAIL M, an open RAIL M license adapted from BigScience and the RAIL Initiative.
Does this model support vision tasks?
No, it is a text‑to‑image diffusion model only.