# ScaleCUA 7B

A Qwen2.5-VL-based computer-use checkpoint with direct grounding and agent action modes across desktop, mobile and web interfaces.

- Catalog URL: https://awesomecua.github.io/resources/url-ff7b1873a3eead89607a/
- Original source: https://huggingface.co/OpenGVLab/ScaleCUA-7B
- Kind: model
- Review: curated
- Scope: core
- Environments: web, desktop, android, linux
- Topics: grounding, action-prediction, planning
- Evidence checked: 2026-10-17T02:45:20Z
- ID: url:ff7b1873a3eead89607a

## Limitations

Four public safetensors shards and model/tokenizer configuration are present. The card declares Apache-2.0. The model card’s Paper link points to the code repository, so the arXiv association uses the repository’s explicit citation rather than treating that link as a paper URL.

- Record JSON: https://awesomecua.github.io/resources/url-ff7b1873a3eead89607a/record.json

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: apache-2.0 — https://huggingface.co/OpenGVLab/ScaleCUA-7B/raw/main/README.md

## Primary evidence

- https://huggingface.co/OpenGVLab/ScaleCUA-7B/raw/main/README.md (retrieved 2026-10-17T02:45:20Z; SHA-256 e45116466b8b9ef3e93992a1efca8fa5b921a8b041297933210c9f552767ffb8)
- https://huggingface.co/api/models/OpenGVLab/ScaleCUA-7B (retrieved 2026-10-17T02:45:19Z; SHA-256 bad2617fd64633212a30b78d99fb053a662378ab50b42722a04af4104ac2248f)
- https://raw.githubusercontent.com/OpenGVLab/ScaleCUA/HEAD/README.md (retrieved 2026-10-17T01:54:55Z; SHA-256 0538701c860afedd5d63c3839039699d8e5a14977d5c339b187ed13ad666c8fa)
- https://huggingface.co/OpenGVLab/ScaleCUA-7B/raw/main/README.md (retrieved 2026-10-17T02:45:20Z; SHA-256 e45116466b8b9ef3e93992a1efca8fa5b921a8b041297933210c9f552767ffb8)