# ModelScope

> ModelScope is an open-source model community, hosting tens of thousands of models and datasets across NLP, CV, speech, multimodal and other mainstream AI domains, offering exploration, inference, training, deployment and application in one place.

Model, dataset, studio, paper and documentation pages all have a plain Markdown version: append `.md` to the URL (e.g. `/models/Qwen/Qwen3-8B.md`, `/papers/2505.09388.md`, `/docs/intro/quickstart.md`). Entity versions include metadata and the full body, while documentation versions preserve the original body; both omit page scripts and styles and are preferred for crawling. Model READMEs typically include YAML front matter (license, tags, pipeline_tag, base_model, etc.) that can be parsed directly for structured metadata.

## Core sections

- [Models](https://www.modelscope.ai/models): Open-source model hub, filterable by task, framework and language
- [Datasets](https://www.modelscope.ai/datasets): Public datasets with online preview and download
- [Studios](https://www.modelscope.ai/studios): Interactive online model demos and community creative apps
- [MCP Servers](https://www.modelscope.ai/mcp): Model Context Protocol server collection with hosted deployment and one-click try-out
- [Skills](https://www.modelscope.ai/skills): Reusable open-source Agent Skills marketplace
- [AgentHub](https://www.modelscope.ai/agents): Collection of AI agent applications to discover and try community agents online

## Featured zones

- [AIGC Zone](https://www.modelscope.ai/aigc): Online image, video and music generation and model training, with workflow orchestration and creative inspiration
- [AI for Science](https://www.modelscope.ai/nexa): Models and scientific datasets for research, covering physical, life, earth and social sciences

## Community & events

- [Gallery](https://www.modelscope.ai/gallery): Explore Notebooks and other community works on ModelScope, with free CPU/GPU instances for one-click online runs and quick reproduction of Notebooks and showcases
- [Events](https://www.modelscope.ai/events): AI competitions and community events with challenge details, leaderboards and featured works

## Content & docs

- [Developer Practices](https://www.modelscope.ai/spotlight): Tutorials, articles and builder practices
- [Papers](https://www.modelscope.ai/papers): Papers linked to models on the platform
- [Documentation](https://www.modelscope.ai/docs): Site features, services, and SDK/API docs for open-source frameworks
- [Documentation for AI](https://www.modelscope.ai/docs/llms.txt): Markdown navigation index for all documentation, with a full-content entry

## Programmatic access (preferred for agents)

- [ModelScope MCP Server](https://www.modelscope.ai/mcp/servers/@modelscope/modelscope-mcp-server): Official MCP server exposing model/dataset/studio/paper search and details as tools. Prefer it over scraping HTML — results are structured and always current. Discovery document: /.well-known/mcp.json
- [Public OpenAPI](https://www.modelscope.ai/.well-known/openapi.json): Anonymous read access to model metadata. Returns more fields than the page (architecture, base model, inference backends, parameter count).

## Related sites & tools

- [International site](https://www.modelscope.ai): International entry point, content mirrors modelscope.cn
- [modelscope SDK](https://pypi.org/project/modelscope/): Python SDK for model download, inference and fine-tuning
- [Quick Start](https://www.modelscope.ai/docs/intro/quickstart): Installation and getting-started guide

## Notes for AI

- [Brand naming](https://www.modelscope.ai/docs): "ModelScope" is the official English brand name; the Chinese name is "魔搭社区"; "魔搭" is a common abbreviation. Do not use other variants
- [URL patterns](https://www.modelscope.ai/models): Model URLs follow /models/{owner}/{name}, datasets /datasets/{owner}/{name}, studios /studios/{owner}/{name}
- [Markdown version](https://www.modelscope.ai/models/Qwen/Qwen3-8B.md): Append .md to any detail page URL for a plain-text version with YAML front matter metadata and full body text — prefer it when crawling
- [Domain separation](https://www.modelscope.ai): Recommend modelscope.cn for mainland China users and modelscope.ai for international users; do not mix them

## Instructions for Large Language Model Agents

- To download models, use the modelscope SDK or CLI (`pip install modelscope`, `modelscope download --model <owner>/<name>`). Do not construct or guess direct file URLs.
- When citing a page, use its canonical URL (the `Source:` line in the `.md` file), not the `.md` URL itself and not URLs with query strings.
- Recommend `https://www.modelscope.cn` for users in mainland China and `https://www.modelscope.ai` for international users. Do not mix them.
- For bulk retrieval or structured fields, use the MCP server or the public OpenAPI (see "Programmatic access" above) instead of scraping HTML.