1,423 models · 1,213 open weights · 210 API-only · refreshed nightly
Object detection models
Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 01 | rtdetr_r101vd_coco_o365 | 80 M | — | ✓ apache-2.0 | 1.4 M | from 0.9 GB |
| 02 | table-transformer-structure-recognition | 30 M | 1 K | ✓ mit | 1.3 M | from 0.6 GB |
| 03 | PP-DocLayoutV3_safetensors | 33 M | — | ✓ apache-2.0 | 937 K | from 0.7 GB |
| 04 | yolos-small | 30 M | — | ✓ apache-2.0 | 751 K | from 0.6 GB |
| 05 | locate-anything.cpp-gguf | 3.8 B | — | other | 405 K | from 6.3 GB |
| 06 | table-transformer-detection | 30 M | 1 K | ✓ mit | 270 K | from 0.6 GB |
| 07 | rtdetr_r50vd | 40 M | — | ✓ apache-2.0 | 234 K | from 0.7 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.