sd3.5 medium needs about 2.5 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 17 quants, from 1.0 GB (Q1_0) to 4.9 GB (F16).
Stable Diffusion 3.5 Medium quantized for efficient image generation
sd3.5 medium is a 2.47B‑parameter Stable Diffusion model quantized into GGUF format. It supports 8k context and can run on a range of hardware. The model is available in multiple quantization levels from Q1_0 to F16.
Good at
- Fast inference on low‑end GPUs
- Compact file sizes
- Good image quality at moderate memory
Limits
- No vision support
- Requires 8k context for full performance
- License is other, not open source
Best for
- Low‑budget image generation
- Edge device inference
- Batch image creation
Who it’s for. Developers and hobbyists who need a balance between speed and quality on limited hardware. It is suitable for users who prefer GGUF quantized models and do not require vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q1_0 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q2_0 | 1.1 GB | 1.7 GB | Fits | Get file → | |
| Q2_K | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_L | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q4_0 | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q4_1 | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q5_0 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q5_K_S | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q5_K_M | 2.1 GB | 2.8 GB | Fits | Get file → | |
| Q5_1 | 2.2 GB | 2.9 GB | Fits | Get file → | |
| Q6_K | 2.3 GB | 3.1 GB | Fits | Get file → | |
| Q8_0 | 2.9 GB | 3.7 GB | Fits | Get file → | |
| F16 | 4.9 GB | 6.0 GB | Fits | Get file → |
For 8 GB VRAM, Q4_0 or Q4_K_S (1.74 GB, ~2.5 GB memory) is recommended. If 4 GB VRAM is available, use Q3_K_S (1.45 GB, ~2.1 GB memory). For CPU‑only inference, Q1_0 (0.96 GB, ~1.6 GB memory) offers the lightest footprint.
What GPU do you need for sd3.5 medium?
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 (2.9 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (4.9 GB file, about 6.0 GB in use).
Which sd3.5 medium quant should you choose?
Q4_K_M is the usual starting point for sd3.5 medium: it balances file size and quality well. Here it is a 1.8 GB file.
The Q8_0 file is 2.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q1_0 at 1.0 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about sd3.5 medium
How much VRAM does sd3.5 medium need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.8 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 sd3.5 medium on an 8 GB GPU?
Yes, with F16: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sd3.5 medium GGUF?
It depends on the quant: Q1_0 is 1.0 GB, Q2_0 is 1.1 GB, Q2_K is 1.2 GB, Q3_K_S is 1.4 GB, Q3_K_L is 1.5 GB, Q3_K_M is 1.5 GB and 11 more.
Where can I download sd3.5 medium GGUF?
The files are on Hugging Face in the calcuis/sd3.5-medium-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 sd3.5 medium 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 sd3.5 medium on 8 GB VRAM?
Yes, using Q4_0 or Q4_K_S which require about 2.5 GB memory at 8k context.
What is the smallest quantization I can use?
Q1_0 is the smallest, 0.96 GB file size and about 1.6 GB memory at 8k context.
Does this model support vision tasks?
No, sd3.5 medium does not have vision capabilities.