ST

stable diffusion v2 1 turbo

StableGGUF by gpustackUpdated 2024-11-21
Download on Hugging Face
Parameters1.29B
Context—
Layers—
Architecture—
Smallest quant2.2 GB
Quick answer

stable diffusion v2 1 turbo needs about 3.0 GB of memory at Q4_1 (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.2 GB (Q4_0) to 2.6 GB.

Stable Diffusion v2 1 Turbo – fast text-to-image generation

Stable Diffusion v2 1 Turbo is a distilled version of Stable Diffusion 2.1 designed for real‑time synthesis. It uses Adversarial Diffusion Distillation to produce high‑quality images in 1–4 steps. The model is available in GGUF format for efficient inference.

Good at

  • Real‑time image generation
  • High fidelity in few steps
  • Compact model size

Limits

  • No vision support
  • License not specified
  • Limited to text prompts

Best for

  • Rapid prototyping
  • Low‑latency image generation
  • Research on distilled diffusion models

Who it’s for. Researchers and developers needing a lightweight, fast text‑to‑image model. Suitable for experimentation and low‑resource deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.2 GB 2.9 GB
Fits Get file →
Q4_12.2 GB 3.0 GB
Fits Get file →
Q8_02.3 GB 3.1 GB
Fits Get file →
—2.6 GB 3.4 GB
Fits Get file →

For 8 GB VRAM, Q4_0 (2.19 GB, 2.9 GB memory) is recommended. Q4_1 (2.2 GB, 3 GB memory) fits 8 GB as well. Q8_0 (2.32 GB, 3.1 GB memory) also works if slightly more VRAM is available. Estimates are approximate.

What GPU do you need for stable diffusion v2 1 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: the best quant that fits is the main file (2.6 GB file, about 3.4 GB in use).

Which stable diffusion v2 1 turbo quant should you choose?

Q4_1 (2.2 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 2.2 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

Parameters1.29B

Source

Quantized bygpustack
FamilyStable
Downloads (HF)2,186
Last updated2024-11-21

Frequently asked questions about stable diffusion v2 1 turbo

How much VRAM does stable diffusion v2 1 turbo need?

About 3.0 GB at Q4_1 with an 8K context window. That is the 2.2 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 v2 1 turbo on an 8 GB GPU?

Yes, with the smaller files: the 2.6 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of stable diffusion v2 1 turbo GGUF?

It depends on the quant: Q4_0 is 2.2 GB, Q4_1 is 2.2 GB, Q8_0 is 2.3 GB, file is 2.6 GB.

Where can I download stable diffusion v2 1 turbo GGUF?

The files are on Hugging Face in the gpustack/stable-diffusion-v2-1-turbo-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Stable Diffusion v2 1 Turbo on 8 GB VRAM?

Yes, the Q4_0 and Q4_1 quantizations use about 2.9–3 GB of VRAM at 8k context, fitting within 8 GB.

What is the file size of the model?

The Q4_0 quantization file is 2.19 GB, Q4_1 is 2.2 GB, Q8_0 is 2.32 GB, and an unknown quant is 2.58 GB.

Does the model support vision tasks?

No, the model is a generative text‑to‑image model and does not support vision inputs.

Similar models

Browse all →

More from gpustack

All by gpustack →

More Stable models

All Stable →

Other tiny models

All tiny models →