ST

stable diffusion v3 5 large

StableGGUF by gpustackUpdated 2024-11-23
Download on Hugging Face
Parameters13.9B
Context—
Layers—
Architecture—
Smallest quant8.3 GB
Quick answer

stable diffusion v3 5 large needs about 14.4 GB of memory at Q4_1 (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 8.3 GB (Q4_0) to 27.9 GB.

Stable Diffusion 3.5 Large – 13.9B parameter text‑to‑image model

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer that generates images from text prompts. It uses three fixed, pretrained text encoders and QK‑normalization for improved stability. The model is released under the Stability Community License.

Good at

  • High image quality
  • Complex prompt understanding
  • Resource‑efficient inference

Limits

  • No vision support beyond text prompts
  • Requires at least 8.32 GB file size
  • License limits commercial use to <$1M revenue

Best for

  • Creative image generation
  • Prompt‑based illustration
  • Rapid prototyping of visual concepts

Who it’s for. Researchers and developers needing a high‑quality text‑to‑image model for local inference. The model is suitable for non‑commercial projects and small‑business commercial use under the community license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_08.3 GB 9.8 GB
Too big Get file →
Q4_011.9 GB 13.9 GB
Too big Get file →
Q4_112.4 GB 14.4 GB
Too big Get file →
Q8_015.2 GB 17.5 GB
Too big Get file →
Q8_015.9 GB 18.4 GB
Too big Get file →
—27.9 GB 31.7 GB
Too big Get file →

For 8 GB VRAM use the Q4_0 quantization with file size 8.32 GB, estimated memory 9.8 GB. For 12 GB VRAM use Q4_0 11.94 GB, estimated memory 13.9 GB. For 16 GB VRAM use Q8_0 15.18 GB, estimated memory 17.5 GB. Memory estimates are approximate.

What GPU do you need for stable diffusion v3 5 large?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q4_0 (8.3 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (12.4 GB file, about 14.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.9 GB file, about 18.4 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (27.9 GB file, about 31.7 GB in use).

Which stable diffusion v3 5 large quant should you choose?

Q4_1 (12.4 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 8.3 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

Parameters13.9B

Source

Quantized bygpustack
FamilyStable
Licenseother
Downloads (HF)1,130
Last updated2024-11-23

Frequently asked questions about stable diffusion v3 5 large

How much VRAM does stable diffusion v3 5 large need?

About 14.4 GB at Q4_1 with an 8K context window. That is the 12.4 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 v3 5 large on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of stable diffusion v3 5 large GGUF?

It depends on the quant: Q4_0 is 8.3 GB, Q4_0 is 11.9 GB, Q4_1 is 12.4 GB, Q8_0 is 15.2 GB, Q8_0 is 15.9 GB, file is 27.9 GB.

Where can I download stable diffusion v3 5 large GGUF?

The files are on Hugging Face in the gpustack/stable-diffusion-v3-5-large-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 v3 5 large 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 Stable Diffusion 3.5 Large on 8 GB VRAM?

Yes, using the Q4_0 quantization (8.32 GB file) which requires approximately 9.8 GB of VRAM.

Is the model suitable for commercial use?

The Stability Community License allows commercial use for organizations or individuals with less than $1M in annual revenue.

What is the recommended quantization for 16 GB VRAM?

Use Q8_0 quantization (15.18 GB file) which estimates 17.5 GB of VRAM usage.

Similar models

Browse all →

More from gpustack

All by gpustack →

More Stable models

All Stable →

Other medium models

All medium models →