Check my GPU →

sd_xl_base_1.0.safetensors

The 16-bit file of SDXL 1.0: 6.9 GB, about 7.1 GB of VRAM to run without offloading. It goes in models/checkpoints.

6.9 GBmodels/checkpointsSDXL
Filesd_xl_base_1.0.safetensors
ModelSDXL 1.0 (image model, 3.5B)
Precision16-bit
Size6.9 GB
VRAM to fitabout 7.1 GB
FolderComfyUI/models/checkpoints/
Loader nodeLoad Checkpoint (CheckpointLoaderSimple)
Sourcestabilityai/stable-diffusion-xl-base-1.0 on Hugging Face

Download sd_xl_base_1.0.safetensors (6.9 GB)

Where to put it

Put the file in ComfyUI/models/checkpoints/ (portable version: ComfyUI_windows_portable/ComfyUI/models/checkpoints/).

Which graphics cards it fits

VRAMThis fileBest file for that card (RTX 40/50)
6 GBOffload onlyShort by 1.1 GB: runs with part of it in system RAM, slowerthis file
8 GBRuns wellFits in VRAM, 0.9 GB to sparethis file
10 GBRuns wellFits in VRAM, 2.9 GB to sparethis file
12 GBRuns wellFits in VRAM, 4.9 GB to sparethis file
16 GBRuns wellFits in VRAM, 8.9 GB to sparethis file
20 GBRuns wellFits in VRAM, 12.9 GB to sparethis file
24 GBRuns wellFits in VRAM, 16.9 GB to sparethis file
32 GBRuns wellFits in VRAM, 24.9 GB to sparethis file
48 GBRuns wellFits in VRAM, 40.9 GB to sparethis file

Need = file × 1 + 1.2 GB for the picture and 0.8 GB for Windows and the browser - the same rule as the rest of the site.

What else you need

This file alone does not make a picture. With it you load:

RoleFileSizeFolder
Checkpointsd_xl_base_1.0.safetensors6.9 GBmodels/checkpoints

6.9 GB in total. Smaller text-encoder versions and other options are on the SDXL page.

Other files of SDXL

FilePrecisionSizeVRAM to fit
sd_xl_base_1.0.safetensors16-bit6.9 GB7.1 GB

Want the answer for your exact card? Check your GPU. Every file of every model: ComfyUI model files.

Size and source read from Hugging Face (2026-10-01).