mask2former-swin-tiny-coco-instance
Mask2Former model trained on COCO instance segmentation (tiny-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
50 M
Context
—
Downloads 30d
211 K
Likes
18
Download history
daily snapshots · 56 days
▲ 0 in the last 30 days (0.0%)
211 K211 K
Aug 23Sep 2Sep 12Sep 21
212 K211 K
Jul 28Aug 15Sep 3Sep 21
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 | 0.2 GB | 0.7 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
- 50 M
- Tensor type
- F32
- Layers / heads
- 10 / 8
- Licence
- other
- First seen on the Hub
- 2022-12-23
- Training datasets
- coco
- Added to our catalog
- 2026-07-28
Compare with any image-segmentation model