Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Can the RTX 3090 24 GB run Stable Diffusion 3.5 Large?

Image model · 8.1B24 GB GDDR6X · 384-bit · 936 GB/s · AmpereData 2026-09-25
Runs well
Yes — and comfortably.

Download 16-bit (16.5 GB). With the model's working memory it needs about 18.8 GB, leaving 5.2 GB spare on 24 GB. Quality: the original weights.

Best file16-bit
File size16.5 GB
VRAM needed~18.8 GB
System RAM32 GB+
Memory map · RTX 3090 24 GB18.8 GB / 24 GB
012 GB24 GB
Weights 16-bit · 16.5 GBWorking memory · 1.5 GBReserve · 0.8 GBFree · 5.2 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
Modelsd3.5_large.safetensors
16-bit · stabilityai/stable-diffusion-3.5-large
models/diffusion_models16.5 GBDownload →
Text encodert5xxl_fp8_e4m3fn.safetensors
T5-XXL FP8 · Comfy-Org/stable-diffusion-3.5-fp8
models/text_encoders4.9 GBDownload →
Text encoderclip_l.safetensors
CLIP-L · Comfy-Org/stable-diffusion-3.5-fp8
models/text_encoders0.2 GBDownload →
Text encoderclip_g.safetensors
CLIP-G · Comfy-Org/stable-diffusion-3.5-fp8
models/text_encoders1.4 GBDownload →
Total download · keep about the same free on disk23.0 GB

Alternatives: T5-XXL FP16 (9.8 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 23.0 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 29.0 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every SD 3.5 Large file on 24 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · stabilityai
16.5 GB18.8 GBfits · 5.2 GB sparethe original weightsHugging Face →
Q8_0
GGUF · city96
8.8 GB11.1 GBfits · 12.9 GB sparepractically identical to the originalHugging Face →
Q5_1
GGUF · city96
6.3 GB8.6 GBfits · 15.4 GB spareclose; small differences in fine detailHugging Face →
Q4_1
GGUF · city96
5.3 GB7.6 GBfits · 16.4 GB sparegood; some loss in fine detail and textHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.5 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

CLIP-L + CLIP-G + T5-XXL: 9.8 GB as 16-bit, 4.9 GB as FP8 (T5-XXL sizes shown; CLIP-L and CLIP-G add about 1.6 GB). ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 24 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

The RTX 3090 24 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain — Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.

RTX 3090 24 GB: 24 GB GDDR6X · 384-bit · 936 GB/s · Ampere. Everything that runs on the RTX 3090 24 GB →

05What more VRAM would change

Nothing to gain for this model: the RTX 3090 24 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.

What changes from the RTX 3090 24 GB to the RTX 4090 24 GB → · What changes from the RTX 3090 24 GB to the RTX 5090 32 GB →

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run SD 3.5 Large on a RTX 3090 24 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does SD 3.5 Large need?

Around 7.6 GB with the smallest file (Q4_1) and 11.1 GB with an 8-bit file (Q8_0), counting working memory and a small system reserve. The full 16-bit file needs about 18.8 GB.

Which SD 3.5 Large file should I download for the RTX 3090 24 GB?

16-bit (16.5 GB) from stabilityai/stable-diffusion-3.5-large.

Is FP8 faster than GGUF on the RTX 3090 24 GB?

No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.

How much do I need to download for SD 3.5 Large on the RTX 3090 24 GB?

About 23.0 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 24 GB card, 32 GB of system RAM or more is recommended.