Can the RTX 5090 32 GB run SDXL 1.0?
Yes. 16-bit fits on the RTX 5090 32 GB with 24.9 GB to spare.
16-bit (6.9 GB) needs about 7.1 GB in use, so 24.9 GB of the 32 GB stays free: room for a larger image, a LoRA or a ControlNet.
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 from Hugging Face, 2026-10-01.
02Every SDXL file on 32 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · stabilityai | 6.9 GB | 7.1 GB | fits · 24.9 GB spare | the original weights | Hugging Face → |
“Needed” adds 1.2 GB of working memory for SDXL and a 0.8 GB reserve. Sizes 2026-10-01. 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.
04Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run SDXL on a RTX 5090 32 GB, send your time per image and peak VRAM and it will appear here, credited.
05About the RTX 5090 32 GB
The RTX 5090 32 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.
32 GB GDDR7 · 512-bit · 1792 GB/s · Blackwell. Everything that runs on it →
06Questions
How much VRAM does SDXL need?
Around 7.1 GB with the smallest file (16-bit).
Which SDXL file should I download for the RTX 5090 32 GB?
16-bit (6.9 GB) from stabilityai/stable-diffusion-xl-base-1.0.
How much do I need to download for SDXL on the RTX 5090 32 GB?
6.9 GB: sd_xl_base_1.0.safetensors.