Can the RTX 3070 8 GB run Stable Diffusion 1.5?
Yes. 16-bit fits on the RTX 3070 8 GB with 4.7 GB to spare.
Take 16-bit (2.1 GB). In use it comes to about 3.3 GB, with 4.7 GB left over on 8 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Checkpoint | v1-5-pruned-emaonly-fp16.safetensors 16-bit · Comfy-Org/stable-diffusion-v1-5-archive | models/checkpoints | 2.1 GB | Download → |
| Total download · keep about the same free on disk | 2.1 GB | |||
One file: the checkpoint already contains the text encoders and the VAE. Sizes from Hugging Face, 2026-10-01.
02Every SD 1.5 file on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 2.1 GB | 3.3 GB | fits · 4.7 GB spare | the original weights | Hugging Face → |
“Needed” adds 0.8 GB of working memory for SD 1.5 and a 0.8 GB reserve. Sizes 2026-10-01. The 2.13 GB checkpoint also holds the text encoder and VAE; the UNet alone is about 1.7 GB at 16-bit.
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 SD 1.5 on a RTX 3070 8 GB, send your time per image and peak VRAM and it will appear here, credited.
05About the RTX 3070 8 GB
The RTX 3070 8 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.
8 GB GDDR6 · 256-bit · 448 GB/s · Ampere. Everything that runs on it →
06Questions
How much VRAM does SD 1.5 need?
Around 3.3 GB with the smallest file (16-bit).
Which SD 1.5 file should I download for the RTX 3070 8 GB?
16-bit (2.1 GB) from Comfy-Org/stable-diffusion-v1-5-archive.
How much do I need to download for SD 1.5 on the RTX 3070 8 GB?
2.1 GB: v1-5-pruned-emaonly-fp16.safetensors.