mask2former-swin-large-ade-semantic vs RMBG-1.4

Specs, VRAM requirements and download trends — updated 6 August 2026.

facebook · A

Params

220 M

Context

—

30d

625 K

briaai · B

Params

40 M

Context

—

30d

319 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	mask2former-swin-large-ade-semantic	RMBG-1.4
Parameters	220 M	40 M
Architecture	Mask2FormerForUniversalSegmentation	BriaRMBG
Context length	—	—
Licence	other	other
Commercial use	Unknown	Unknown
Languages	—	—
Downloads 30d	624,580	318,612
Downloads all time	4.1 M	16.9 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2023-01-05	2023-12-12

Daily snapshots, last 10 days (28 Jul – 6 Aug)

675 K286 K

mask2former-swin-large-ade-semantic RMBG-1.4

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

RMBG-1.4 · fp16 0.7 GB / 24 GB

✅ Runs comfortably

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

✅ Runs comfortably