🤖 Hugging Face Model Scraper

🚀 Collect AI model data from Hugging Face Hub in minutes. Search by keyword, task, library, license, or language. Export model names, downloads, likes, tags, and metadata. No coding, no Hugging Face account required.

🕒 Last updated: 2026-04-23 · 📊 20+ fields per model · 🔍 5 search filters · 📊 Download + like counts · 🚫 No auth required

The Hugging Face Model Scraper collects model metadata from the Hugging Face Hub, returning 20+ fields per model: model ID, author, task type, library (PyTorch, TensorFlow, JAX), license, downloads, likes, tags, languages, pipeline tag, and model card URL. Supports keyword search with task, library, license, and language filters.

Hugging Face hosts over 800,000 AI models. This Actor queries the Hub and returns structured data ready for model scouting, benchmarking, or research dashboards.

🎯 Target Audience	💡 Primary Use Cases
ML engineers, AI researchers, data scientists, MLOps teams, AI product managers, VC analysts	Model scouting, benchmarking, competitive analysis, library adoption tracking, license auditing

---

📋 What the Hugging Face Model Scraper does

Five search filters:

• 🔍 Keyword search. Free-text search across model names and cards.
• 🎯 Task filter. Text generation, image classification, translation, summarization, and more.
• 📚 Library filter. PyTorch, TensorFlow, JAX, ONNX, Flax, etc.
• 📜 License filter. MIT, Apache 2.0, proprietary, custom licenses.
• 🌐 Language filter. English, Chinese, multilingual, etc.

Each model record includes model ID, author, task, library, license, downloads, likes, tags, languages, pipeline tag, last modified date, and model card URL.

💡 Why it matters: browsing Hugging Face for model comparisons means clicking through hundreds of model cards. This Actor exports structured model metadata at scale for ML benchmarking, scouting, and ecosystem analysis.

---

🎬 Full Demo

🚧 Coming soon: a 3-minute walkthrough showing how to go from sign-up to a downloaded dataset.

---

⚙️ Input

Input	Type	Default	Behavior
query	string	""	Search across model names and cards.
task	string	""	Task type: text-generation, image-classification, etc.
library	string	""	ML library: transformers, diffusers, ONNX, etc.
license	string	""	License: MIT, Apache 2.0, etc.
language	string	""	Model language: en, zh, multilingual.

Example: text generation models with Apache 2.0 license.

{
    "query": "llama",
    "task": "text-generation",
    "license": "apache-2.0"
}

Example: image classification models in PyTorch.

{
    "task": "image-classification",
    "library": "transformers"
}

⚠️ Good to Know: Hugging Face model downloads can change rapidly. Each run captures a point-in-time snapshot of the Hub's metadata.

---

📊 Output

Each model record contains 20+ fields. Download the dataset as CSV, Excel, JSON, or XML.

🧾 Schema

Field	Type	Example
🤖 modelId	string	"meta-llama/Llama-3-8B"
👤 author	string	"meta-llama"
🎯 task	string	"text-generation"
📚 library	string	"transformers"
📜 license	string	"llama3"
📊 downloads	number	5000000
👍 likes	number	12000
🏷️ tags	array	["llm", "text-generation"]
🌐 languages	array	["en"]
🏷️ pipelineTag	string	"text-generation"
📅 lastModified	string	"2026-03-15T10:30:00Z"
📂 modelCardUrl	string	"https://huggingface.co/meta-llama/..."
🔗 url	string	"https://huggingface.co/meta-llama/Llama-3-8B"
🕒 scrapedAt	ISO 8601	"2026-04-16T00:00:00.000Z"

📦 Sample records

---

✨ Why choose this Actor

	Capability
🤖	800,000+ models. Full Hugging Face Hub coverage.
🔍	5 search filters. Keyword, task, library, license, language.
📊	Popularity metrics. Downloads and likes per model.
📜	License data. License type per model for compliance auditing.
📚	Library tracking. PyTorch, TensorFlow, JAX adoption data.
⚡	Scalable. From single lookups to full task-type sweeps.
🚫	No authentication. Public Hub API.

📊 Hugging Face hosts over 800,000 AI models. Structured access to this metadata powers every ML benchmarking, model scouting, and ecosystem analysis workflow.

---

📈 How it compares to alternatives

Approach	Cost	Coverage	Refresh	Filters	Setup
⭐ Hugging Face Model Scraper (this Actor)	$5 free credit, then pay-per-use	Full Hub	Live per run	keyword, task, library, license, language	⚡ 2 min
Hugging Face Hub API (direct)	Free with rate limits	Full	Real-time	Many	⏳ Hours (API client setup)
Manual Hub browsing	Free	Manual	Manual	UI only	🕒 Hours per category
Paid AI model databases	$100-1,000/month	Multi-source	Varies	Many	🐢 Days

Pick this Actor when you want Hugging Face model data on demand, with task and library filters, without writing API client code.

---

🚀 How to use

1. 📝 Sign up. Create a free account with $5 credit (takes 2 minutes).
2. 🌐 Open the Actor. Go to the Hugging Face Model Scraper page on the Apify Store.
3. 🎯 Set input. Enter keywords, pick a task and library.
4. 🚀 Run it. Click Start and let the Actor collect your data.
5. 📥 Download. Grab your results in the Dataset tab as CSV, Excel, JSON, or XML.

⏱️ Total time from signup to downloaded dataset: 3-5 minutes. No coding required.

---

💼 Business use cases

🤖 ML Engineering & Research Scout models for specific tasks Compare download trends across architectures Track new model releases by library Audit license compliance for production use	📊 AI Market Intelligence Track AI model ecosystem growth Analyze library adoption rates (PyTorch vs TF) Monitor competitor model releases Build AI investment thesis datasets
🏢 MLOps & Platform Teams Build internal model catalogs Track community model updates Monitor license changes across dependencies Benchmark model sizes and performance	💼 VC & Strategy Teams Map the AI model landscape by task Track emerging architectures and frameworks Analyze open-source AI momentum Build competitive maps of AI model builders

---

---

🌟 Beyond business use cases

Data like this powers more than commercial workflows. The same structured records support research, education, civic projects, and personal initiatives.

🎓 Research and academia Empirical datasets for papers, thesis work, and coursework Longitudinal studies tracking changes across snapshots Reproducible research with cited, versioned data pulls Classroom exercises on data analysis and ethical scraping	🎨 Personal and creative Side projects, portfolio demos, and indie app launches Data visualizations, dashboards, and infographics Content research for bloggers, YouTubers, and podcasters Hobbyist collections and personal trackers
🤝 Non-profit and civic Transparency reporting and accountability projects Advocacy campaigns backed by public-interest data Community-run databases for local issues Investigative journalism on public records	🧪 Experimentation Prototype AI and machine-learning pipelines with real data Validate product-market hypotheses before engineering spend Train small domain-specific models on niche corpora Test dashboard concepts with live input

🤖 Ask an AI assistant about this scraper

Open a ready-to-send prompt about this ParseForge actor in the AI of your choice:

• 💬 ChatGPT
• 🧠 Claude
• 🔍 Perplexity
• 🅒 Copilot

❓ Frequently Asked Questions

---

🔌 Automating Hugging Face Model Scraper

Control the scraper programmatically for scheduled runs and pipeline integrations:

• 🟢 Node.js. Install the apify-client NPM package.
• 🐍 Python. Use the apify-client PyPI package.
• 📚 See the Apify API documentation for full details.

The Apify Schedules feature lets you trigger this Actor on any cron interval. Weekly pulls keep your model intelligence database fresh.

🔌 Integrate with any app

Hugging Face Model Scraper connects to any cloud service via Apify integrations:

• Make - Automate multi-step workflows
• Zapier - Connect with 5,000+ apps
• Slack - Get run notifications in your channels
• Airbyte - Pipe model data into your warehouse
• GitHub - Trigger runs from commits and releases
• Google Drive - Export datasets straight to Sheets

You can also use webhooks to trigger downstream actions when a run finishes. Push fresh model data into your ML platform, or alert your team in Slack.

---

🔗 Recommended Actors

• 📚 Semantic Scholar Scraper - Academic paper data
• 📝 HTML to JSON Smart Parser - AI data extraction
• 🎤 Audio Transcriber - Speech to text
• 🎨 Modern Manga Colorizer - AI manga colorization
• 💼 HubSpot Marketplace Scraper - Marketplace data

💡 Pro Tip: browse the complete ParseForge collection for more AI and data scrapers.

---

🆘 Need Help? Open our contact form to request a new scraper, propose a custom data project, or report an issue.

---

⚠️ Disclaimer: this Actor is an independent tool and is not affiliated with, endorsed by, or sponsored by Hugging Face, Inc. All trademarks mentioned are the property of their respective owners. Only publicly available Hub metadata is collected.