Skip to main content
Hugging Face Hub — Top 10,000 Models By Downloads (Task, Library, Licence, Likes)
DatasetCSV.GZOpenHuggingfaceAI ModelsLLMMachine LearningOpen SourceRankingsFree
10,000 most-downloaded models on the Hugging Face Hub ranked by 30-day downloads, with repository id, author, pipeline task, library, downloads, likes, creation and last-modified timestamps, licence tag, gating flag and tag count, from the public Hub API as of 2026-09-06.
Use Cases
- Open-model adoption tracking
- Library and task mix of the ecosystem
- Licence screening for model selection
- Watchlists of fast-rising models
Methodology
Ten cursor-paginated pages of 1,000 models sorted by downloads, following the Link rel=next header; licence read from the license: tag; gated is true for both auto and manual gating.
Update Schedule
Static snapshot. Hub download counts are rolling 30-day figures that change daily; refresh weekly.
Attribution
Source: Hugging Face Hub public API (huggingface.co/api/models); repository metadata only, each model carries its own licence.
Schema
| name | type |
|---|---|
| rank | integer |
| model_id | string |
| author | string |
| pipeline_tag | string |
| library_name | string |
| downloads | integer |
| likes | integer |
| created_at | date |
| last_modified | date |
| license | string |
| gated | boolean |
| tag_count | integer |
Sample Data
| rank | gated | likes | author | license | model_id | downloads | tag_count | created_at | library_name | pipeline_tag | last_modified |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | false | 5560 | sentence-transformers | apache-2.0 | sentence-transformers/all-MiniLM-L6-v2 | 253029336 | 47 | 2022-03-02T23:29:05.000Z | sentence-transformers | sentence-similarity | 2026-06-01T06:29:13.000Z |
| 2 | false | 311 | cross-encoder | apache-2.0 | cross-encoder/ms-marco-MiniLM-L6-v2 | 86493507 | 18 | 2022-03-02T23:29:05.000Z | sentence-transformers | text-ranking | 2026-08-09T15:22:24.000Z |
| 3 | false | 548 | BAAI | mit | BAAI/bge-small-en-v1.5 | 65591890 | 22 | 2023-09-12T05:20:55.000Z | sentence-transformers | feature-extraction | 2024-02-22T03:36:23.000Z |
| 4 | false | 158 | apache-2.0 | google/electra-base-discriminator | 58408339 | 12 | 2022-03-02T23:29:05.000Z | transformers | 2024-02-29T10:20:20.000Z | ||
| 5 | false | 2986 | google-bert | apache-2.0 | google-bert/bert-base-uncased | 52338347 | 20 | 2022-03-02T23:29:04.000Z | transformers | fill-mask | 2024-02-19T11:06:12.000Z |
Get this via API
# 1. Add dAgentBase once, in any MCP client. No install, no vendor keys.
# Claude.ai / Claude Desktop: Settings -> Connectors -> Add custom connector
# Cursor / Claude Code / others: mcp.json
{
"mcpServers": {
"dagentbase": {
"url": "https://dagentbase.com/api/mcp",
"headers": { "Authorization": "Bearer dm_live_YOUR_KEY" }
}
}
}
# 2. Then ask your agent, in plain language:
# "Preview 'Hugging Face Hub — Top 10,000 Models by Downloads (Task, Library, Licence, Likes)' and, if it fits, claim it and download the files."
# Tools it will use: search_listings -> preview_listing -> purchase_listing -> get_download_urls
# 1. Add dAgentBase once, in any MCP client. No install, no vendor keys.
# Claude.ai / Claude Desktop: Settings -> Connectors -> Add custom connector
# Cursor / Claude Code / others: mcp.json
{
"mcpServers": {
"dagentbase": {
"url": "https://dagentbase.com/api/mcp",
"headers": { "Authorization": "Bearer dm_live_YOUR_KEY" }
}
}
}
# 2. Then ask your agent, in plain language:
# "Preview 'Hugging Face Hub — Top 10,000 Models by Downloads (Task, Library, Licence, Likes)' and, if it fits, claim it and download the files."
# Tools it will use: search_listings -> preview_listing -> purchase_listing -> get_download_urlsFree
one time · open license
Details
Rows10,000
Size418 KB
Files1
FormatCSV.GZ
Available formats
CSV.GZ418 KB
Freeopen