Hugging Face Trending Models, Datasets & Spaces Tracker

What does HuggingFace Model Tracker do?

HuggingFace Model Tracker is an Apify Actor that monitors trending and top-downloaded AI models, datasets, and Spaces on the Hugging Face Hub in real time — no API key required. It pulls live data from the public HF Hub API and returns structured records for every item including download counts, likes, trending scores, license, tags, gated status, and direct Hub URLs. Whether you are tracking the latest open source LLM releases from Meta, Mistral, Google, or Microsoft, or monitoring fast-rising research models before they go viral, this Actor delivers a clean feed of AI model releases on demand.

Why use HuggingFace Model Tracker?

The Hugging Face Hub publishes hundreds of new models every day. Manually tracking what is trending across text-generation, image-to-text, speech recognition, and dozens of other tasks is impractical without automation. Key business use cases:

• LLM release monitoring — get instant alerts when major labs (Meta, Mistral, Google DeepMind, Microsoft) push new models to the Hub. Filter by authorFilter to watch specific organizations.
• Research trend detection — track fast-rising models by trending_score before they accumulate mass downloads. Discover breakout architectures and techniques weeks before the broader community notices.
• Competitive intelligence — compare download counts, likes, and trending velocity across competing model families (e.g. Llama vs. Mistral vs. Gemma) for product strategy decisions.
• Dataset discovery for fine-tuning — switch to mode: datasets to find the most popular training and evaluation datasets for your target task, sorted by trending or downloads.
• Space popularity tracking — monitor mode: spaces to discover popular Gradio and Streamlit demos, identify deployment patterns, and find community tools gaining traction.

How to use HuggingFace Model Tracker

1. Open the Actor on Apify Store and click Try for free.
2. Choose a mode — models, datasets, or spaces (default: models).
3. Set a sort order — trending for what is hot right now, downloads for most-used, likes for community favorites, or lastModified for recent activity.
4. Filter by task (optional) — enter a pipeline task tag such as text-generation, image-classification, text-to-image, or automatic-speech-recognition.
5. Filter by author/org (optional) — enter an org slug such as meta-llama, microsoft, google, or mistralai.
6. Set the item limit — 1 to 500. Default is 50.
7. Run and export — results appear in the dataset as flat JSON records, exportable as JSON, CSV, or XLSX.

Input

Field	Type	Default	Description
mode	string	models	What to fetch: models, datasets, or spaces
sortBy	string	trending	Sort order: trending, downloads, likes, lastModified
limit	integer	50	Number of items to fetch (1–500)
search	string	—	Keyword filter applied to name, description, and tags
taskFilter	string	—	Pipeline task tag: text-generation, image-classification, question-answering, text-to-image, automatic-speech-recognition, etc.
authorFilter	string	—	Filter by org or user: meta-llama, microsoft, google, mistralai, stabilityai, etc.
includeDetails	boolean	false	Fetch full model card + file list per item (models only; increases PPE charges)

Example — top 100 trending text-generation models:

{
  "mode": "models",
  "sortBy": "trending",
  "limit": 100,
  "taskFilter": "text-generation"
}

Example — monitor Meta's latest model releases:

{
  "mode": "models",
  "sortBy": "lastModified",
  "limit": 20,
  "authorFilter": "meta-llama"
}

Output

[
  {
    "model_id": "meta-llama/Llama-3.1-8B",
    "author": "meta-llama",
    "name": "Llama-3.1-8B",
    "task": "text-generation",
    "downloads": 12345678,
    "likes": 5678,
    "trending_score": 99.5,
    "tags": ["llm", "pytorch", "transformers"],
    "license": "llama3.1",
    "last_modified": "2026-08-20T18:00:00.000Z",
    "created_at": "2024-07-18T00:00:00.000Z",
    "private": false,
    "gated": false,
    "hf_url": "https://huggingface.co/meta-llama/Llama-3.1-8B",
    "rank": 1,
    "mode": "models",
    "fetched_at": "2026-09-02T09:00:00.000000+00:00"
  },
  {
    "model_id": "mistralai/Mistral-7B-Instruct-v0.3",
    "author": "mistralai",
    "name": "Mistral-7B-Instruct-v0.3",
    "task": "text-generation",
    "downloads": 8901234,
    "likes": 3412,
    "trending_score": 87.2,
    "tags": ["llm", "pytorch", "transformers", "mistral"],
    "license": "apache-2.0",
    "last_modified": "2026-08-18T10:00:00.000Z",
    "created_at": "2024-05-22T00:00:00.000Z",
    "private": false,
    "gated": false,
    "hf_url": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3",
    "rank": 2,
    "mode": "models",
    "fetched_at": "2026-09-02T09:00:00.000000+00:00"
  }
]

Data fields

Field	Type	Description
model_id	string	Full Hub identifier (author/model-name)
author	string	Organization or user that published the model
name	string	Short model name
task	string	Pipeline task (e.g. text-generation, image-classification)
downloads	integer	Total download count (all time)
likes	integer	Number of community likes
trending_score	float	HF internal trending score (higher = more trending; not available for all items)
tags	array	Associated tags (frameworks, domains, languages)
license	string	License identifier (e.g. apache-2.0, mit, llama3.1)
last_modified	string	ISO 8601 timestamp of last Hub update
created_at	string	ISO 8601 timestamp of initial upload
private	boolean	true if the model is private
gated	boolean/string	false, true, "auto", or "manual" — indicates access control level
hf_url	string	Direct Hugging Face Hub URL for the item
rank	integer	Position in the returned list (1 = top result)
mode	string	Which endpoint was queried: models, datasets, or spaces
fetched_at	string	ISO 8601 UTC timestamp of this Actor run

Cost estimation

This Actor uses Pay-Per-Event (PPE) pricing — you pay only for items actually fetched.

Event	Price	Notes
Actor start	$0.005	Charged once per run
Per item fetched	$0.001	Per model, dataset, or space record

Typical run	Items	Estimated cost
50 trending models (default)	50	~$0.055
100 models	100	~$0.105
500 models (full feed)	500	~$0.505
Daily monitor, 50 models/day × 30 days	1,500	~$1.51/month

FAQ

Does this Actor require a Hugging Face account or API token? No. It uses the public Hugging Face Hub API endpoints (/api/models, /api/datasets, /api/spaces), which are freely accessible without authentication. Rate limits are handled automatically with retry logic.

What is trending_score and how is it calculated? trending_score is a Hugging Face internal metric that measures how rapidly a model is gaining downloads and likes relative to its historical baseline. The exact formula is proprietary to HF. Not all items expose this field — expect it to be null for some models.

Can I track new model releases from a specific organization automatically? Yes — schedule this Actor to run daily with sortBy: "lastModified" and your authorFilter set to the organization you want to watch (e.g. meta-llama, google, mistralai). Pair it with an Apify webhook to send new results to Slack, email, or your own API the moment a new model is detected.

---

Disclaimer: Data is fetched from the public Hugging Face Hub API. Download counts, likes, and trending scores reflect the state of the Hub at the time of the Actor run and may change rapidly. trending_score is a Hugging Face internal metric and is not exposed for all items. This Actor has no affiliation with Hugging Face, Inc.

---

Related actors

• AI Model Benchmark Tracker — Benchmark scores for models discovered trending here
• GitHub Trending Tracker — GitHub repos of open-source models for code and community activity
• Semantic Scholar Papers — Research papers behind trending AI models on HuggingFace

Feedback

If this actor powers your AI research, a review helps others find it: Leave a review on Apify Store