Check my GPU

Image models ·

Stable Diffusion 3.5 Large

Backbone
8.1B
Native output
1024×1024
Default steps
28
License
stabilityai-community
Released
2024-10

How to run it

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/city96/stable-diffusion-3.5-large-gguf (opens in a new tab)

Original weights · Hugging Face

Full-precision files from Stability AI, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/stabilityai/stable-diffusion-3.5-large (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

Reference code, inference scripts and docs from Stability AI. The weights themselves download from Hugging Face.

github.com/Stability-AI/sd3.5 (opens in a new tab)

git clone https://github.com/Stability-AI/sd3.5

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision Everything on GPU Text encoder offloaded Sequential offload Download
FP16 30.0 GB 18.8 GB 8.1 GB Original weights (opens in a new tab)
FP8 16.3 GB 10.7 GB 5.3 GB Original weights (opens in a new tab)
Q8 GGUF 16.8 GB 11.3 GB 5.5 GB GGUF (opens in a new tab)
Q4 GGUF 13.0 GB 7.5 GB 4.1 GB GGUF (opens in a new tab)

Components

Best hardware for Stable Diffusion 3.5 Large

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at FP8.

Grade · points Hardware Precision Memory Time per output Fit
84 ptsGreat (A) · 84 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 FP8 16.3 GB / 24.0 GB 9.9 s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 14.3/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX FP8 16.3 GB / 24.0 GB 11 s Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15 NVIDIA GeForce RTX 5090 FP8 16.3 GB / 32.0 GB 8.3 s Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 FP8 16.3 GB / 24.0 GB 19 s Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q4 GGUF 13.0 GB / 16.0 GB 18 s Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q4 GGUF 13.0 GB / 16.0 GB 18 s Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q4 GGUF 13.0 GB / 16.0 GB 19 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 10.3/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q4 GGUF 13.0 GB / 16.0 GB 21 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 10.3/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q4 GGUF 13.0 GB / 16.0 GB 21 s Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 NVIDIA RTX PRO 6000 Blackwell FP16 30.0 GB / 96.0 GB 8.1 s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.