Can the RTX 2060 6 GB run SDXL 1.0?
Not entirely. Even 16-bit is 1.1 GB over 6 GB, so ComfyUI keeps part of it in system RAM.
Nothing fits entirely, but 16-bit (6.9 GB) overflows by only about 1.1 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.
01With more VRAM
With 8 GB you could run SDXL at 8-bit or better (16-bit, 6.9 GB) with no offloading: for example on the RTX 5060 Ti 8 GB, RTX 5060 8 GB, RTX 4060 Ti 8 GB.
What changes from the RTX 2060 6 GB to the RTX 3060 12 GB → · What changes from the RTX 2060 6 GB to the RTX 5060 Ti 16 GB →
02Every SDXL file on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · stabilityai | 6.9 GB | 7.1 GB | spills 1.1 GB | 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.
03What 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.
04The text encoder
The text encoder is inside the checkpoint, so there is nothing extra to download.
05Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run SDXL on a RTX 2060 6 GB, send your time per image and peak VRAM and it will appear here, credited.
06About the RTX 2060 6 GB
The RTX 2060 6 GB (Turing) 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.
6 GB GDDR6 · 192-bit · 336 GB/s · Turing. Everything that runs on it →
07Questions
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 2060 6 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 2060 6 GB?
6.9 GB: sd_xl_base_1.0.safetensors.