PP-DocLayoutV3_safetensors vs table-transformer-structure-recognition-v1.1-all

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

PaddlePaddle · A
Params
30 M
Context
30d
822 K
apache-2.0 · commercial OK
microsoft · B
Params
30 M
Context
30d
240 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification PP-DocLayoutV3_safetensors table-transformer-structure-recognition-v1.1-all
Parameters 30 M 30 M
Architecture PPDocLayoutV3ForObjectDetection TableTransformerForObjectDetection
Context length
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 3
Downloads 30d 822,269 240,245
Downloads all time 2.4 M 18.0 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-01-20 2023-11-18

Download trend

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

830 K240 K
PP-DocLayoutV3_safetensors table-transformer-structure-recognition-v1.1-all

VRAM side by side

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

table-transformer-structure-recognition-v1.1-all · fp16 0.6 GB / 24 GB
✅ Runs comfortably
PP-DocLayoutV3_safetensors · fp16 0.7 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons