mask2former-swin-large-cityscapes-semantic vs oneformer_cityscapes_swin_large
Specs, VRAM requirements and download trends — updated 24 October 2026.
facebook · A · Open weights
Params
220 M
Context
—
30d
377 K
shi-labs · B · Open weights
Params
—
Context
—
30d
184 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | mask2former-swin-large-cityscapes-semantic | oneformer_cityscapes_swin_large |
|---|---|---|
| Parameters | 220 M | — |
| Architecture | Mask2FormerForUniversalSegmentation | OneFormerForUniversalSegmentation |
| Context length | — | — |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 376,758 | 183,668 |
| Downloads all time | 11.1 M | 775 K |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2023-01-05 | 2022-11-15 |
Download trend
89 days of snapshots recorded — chart in 0 days.
11.1 M
mask2former-swin-large-cityscapes-semantic · all-time downloads
775 K
oneformer_cityscapes_swin_large · all-time downloads
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
mask2former-swin-large-cityscapes-semantic · fp16
1.5 GB / 24 GB
Adjacent comparisons
BiRefNet vs mask2former-swin-large-cityscapes-semantic
mask2former-swin-large-ade-semantic vs mask2former-swin-large-cityscapes-semantic
clipseg-rd64-refined vs mask2former-swin-large-cityscapes-semantic
BiRefNet vs oneformer_cityscapes_swin_large
RMBG-2.0 vs mask2former-swin-large-cityscapes-semantic
segformer-b0-finetuned-ade-512-512 vs mask2former-swin-large-cityscapes-semantic