Can the RTX 4090 24 GB run SDXL 1.0?
Download 16-bit (6.9 GB). With the model's working memory it needs about 7.1 GB, leaving 16.9 GB spare on 24 GB. Quality: the original weights.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Checkpoint | sd_xl_base_1.0.safetensors 16-bit · stabilityai/stable-diffusion-xl-base-1.0 | models/checkpoints | 6.9 GB | Download → |
| Total download · keep about the same free on disk | 6.9 GB | |||
One file: the checkpoint already contains the text encoders and the VAE. 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: 16 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 6.9 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 12.9 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every SDXL file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · stabilityai | 6.9 GB | 7.1 GB | fits · 16.9 GB spare | the original weights | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.2 GB working memory for this model + 0.8 GB kept free for the system. The 6.94 GB checkpoint also holds the two text encoders and the VAE. During sampling only the UNet (about 5.1 GB at 16-bit, 2.6B parameters) has to sit in VRAM, so that is the figure used for the 16-bit file.
03The text encoder
The text encoder is inside the checkpoint, so there is nothing extra to download.
04About this GPU
The RTX 4090 24 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)
RTX 4090 24 GB: 24 GB GDDR6X · 384-bit · 1008 GB/s · Ada Lovelace. Everything that runs on the RTX 4090 24 GB →
05What more VRAM would change
Nothing to gain for this model: the RTX 4090 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 4090 24 GB to the RTX 5090 32 GB →
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run SDXL on a RTX 4090 24 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
How much VRAM does SDXL need?
Around 7.1 GB with the smallest file (16-bit), counting working memory and a small system reserve.
Which SDXL file should I download for the RTX 4090 24 GB?
16-bit (6.9 GB) from stabilityai/stable-diffusion-xl-base-1.0.
Is FP8 faster than GGUF on the RTX 4090 24 GB?
It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.
How much do I need to download for SDXL on the RTX 4090 24 GB?
About 6.9 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, 16 GB of system RAM or more is recommended.