Model reference · open weights
swin2SR-compressed-sr-x4-48 is an open-weight image model from caidas. swin2SR-compressed-sr-x4-48 (FP32) weighs 25 MB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the caidas/swin2SR-compressed-sr-x4-48 model card, 2026-10-01
What it is
| Released by | caidas |
|---|---|
| Released | 2022-12-16 |
| Parameters | 12M |
| VRAM | 25 MB for the weights |
What it runs on
| Card | One image | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Swin2SR model that upscales images x4. It was introduced in the paper Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration by Conde et al. and first released in this repository.
This model is intended for compressed image super resolution.
Refer to the documentation.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. How to run this model is on its model card.