facebook / image-segmentation updated 2 years ago

mask2former-swin-large-ade-semantic

Name: mask2former-swin-large-ade-semantic
Author: facebook

Mask2Former model trained on ADE20k semantic segmentation (large-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository.

Params

220 M

Context

—

Downloads 30d

625 K

Likes

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

675 K621 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.9 GB	1.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Mask2FormerForUniversalSegmentation
Parameters: 220 M
Tensor type: F32
Layers / heads: 10 / 8
Licence: other
First seen on the Hub: 2023-01-05
Training datasets: coco
Added to our catalog: 2026-07-28

Compare with

clipseg-rd64-refined 1.1 M BiRefNet 715 K RMBG-2.0 702 K segformer-b0-finetuned-ade-512-512 364 K segformer-b2-finetuned-ade-512-512 338 K RMBG-1.4 319 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB