ST

stable diffusion 3.5 medium turbo

StableGGUF by tensorartUpdated 2025-01-16
Download on Hugging Face
Parameters2.47B
Context—
Layers—
Architecturesd3
Smallest quant1.8 GB
Quick answer

stable diffusion 3.5 medium turbo 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 2 quants, from 1.8 GB (Q4_K_M) to 2.9 GB (Q8_0).

Stable Diffusion 3.5 Medium Turbo – efficient text‑to‑image generation

TensorArt Stable Diffusion 3.5 Medium Turbo is a distilled version of StabilityAI’s stable‑diffusion‑3.5‑medium. It offers fast generation and high‑resolution outputs while remaining lightweight. The model supports a wide range of artistic styles.

Good at

  • Fast generation on modest hardware
  • High‑resolution image creation
  • Versatile artistic styles

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • License is other

Best for

  • Rapid prototyping of art assets
  • Batch image generation
  • Creative experimentation

Who it’s for. Developers and artists who need quick, high‑quality image generation without large GPU memory. The model is suitable for local deployment with moderate resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.8 GB 2.5 GB
Fits Get file →
Q8_02.9 GB 3.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.79 GB file, ~2.5 GB memory at 8k context). For 12 GB VRAM, Q8_0 (2.86 GB file, ~3.7 GB memory at 8k context) provides higher fidelity.

What GPU do you need for stable diffusion 3.5 medium 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 Q8_0 (2.9 GB file, about 3.7 GB in use).

Which stable diffusion 3.5 medium turbo quant should you choose?

Q4_K_M is the usual starting point for stable diffusion 3.5 medium turbo: 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturesd3
Parameters2.47B

Source

Quantized bytensorart
FamilyStable
Licenseother
Downloads (HF)2,396
Last updated2025-01-16

Frequently asked questions about stable diffusion 3.5 medium turbo

How much VRAM does stable diffusion 3.5 medium turbo 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 stable diffusion 3.5 medium turbo on an 8 GB GPU?

Yes, with Q8_0: the 2.9 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of stable diffusion 3.5 medium turbo GGUF?

It depends on the quant: Q4_K_M is 1.8 GB, Q8_0 is 2.9 GB.

Where can I download stable diffusion 3.5 medium turbo GGUF?

The files are on Hugging Face in the tensorart/stable-diffusion-3.5-medium-turbo 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 3.5 medium turbo 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires about 2.5 GB of VRAM at 8k context, fitting within an 8 GB GPU.

Does this model support vision tasks?

No, the model is text‑to‑image only and does not include vision capabilities.

What is the file size of the Q8_0 quantized model?

The Q8_0 quantized model file is 2.86 GB.

Other GGUFs of stable-diffusion-3.5-medium

Similar models

Browse all →

More Stable models

All Stable →

Other tiny models

All tiny models →