mask2former-swin-large-ade-semantic vs segformer-b2-finetuned-ade-512-512

Specs, VRAM requirements and download trends — updated 24 October 2026.

facebook · A · Open weights
Params
220 M
Context
—
30d
336 K
nvidia · B · Open weights
Params
—
Context
—
30d
187 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification mask2former-swin-large-ade-semantic segformer-b2-finetuned-ade-512-512
Parameters 220 M —
Architecture Mask2FormerForUniversalSegmentation SegformerForSemanticSegmentation
Context length — —
Licence other other
Commercial use Unknown Unknown
Languages — —
Downloads 30d 335,778 187,375
Downloads all time 5.3 M 2.2 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2023-01-05 2022-03-02

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

500 K187 K
mask2former-swin-large-ade-semantic segformer-b2-finetuned-ade-512-512 A overtook B on 5 Oct

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

mask2former-swin-large-ade-semantic · fp16 1.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons