Text classification trends · updated Oct 2, 2026

Which open-weight text classification and extraction models get downloaded most

A daily read of Hugging Face's top 5,000 models, focused on models that classify text and pull out information, from base encoders like BERT to entity taggers: the most downloaded, new uploads in the top 5,000, what they are used for, and who makes them.

Most downloaded

The most-downloaded open-weight text classification and extraction models

Ranked by downloads over the last 30 days. Fine-tuned versions count; most format conversions and re-uploads are left out. Counts include automated fetches, which lift models that tools and test suites pull by default. How models are placed is explained under About this data.

#	Model	Maker	Task	Licence	Downloads	Valkyrie
1	bert-base-uncased	google-bert	Base encoders	Apache-2.0	40.6M	Fine-tune one like it →Fine-tune one →
2	xlm-roberta-base	FacebookAI	Base encoders	MIT	16.5M	Fine-tune one like it →Fine-tune one →
3	roberta-base	FacebookAI	Base encoders	MIT	8.0M	Fine-tune one like it →Fine-tune one →
4	distilbert-base-uncased	distilbert	Base encoders	Apache-2.0	7.9M	Fine-tune one like it →Fine-tune one →
5	mdeberta-v3-base	microsoft	Base encoders	MIT	5.6M	Fine-tune one like it →Fine-tune one →
6	roberta-large	FacebookAI	Base encoders	MIT	5.6M	Fine-tune one like it →Fine-tune one →
7	finbert	ProsusAI	Text classification	-	4.6M
8	ModernBERT-base	answerdotai	Base encoders	Apache-2.0	4.3M	Fine-tune one like it →Fine-tune one →
9	Prompt-Guard-86M	meta-llama	Text classification	Llama licence	3.5M	Fine-tune one like it →Fine-tune one →
10	bert-base-cased	google-bert	Base encoders	Apache-2.0	3.5M	Fine-tune one like it →Fine-tune one →
11	bert-base-multilingual-uncased	google-bert	Base encoders	Apache-2.0	3.2M	Fine-tune one like it →Fine-tune one →
12	distilbert-base-uncased-finetuned-sst-2-english	distilbert	Text classification	Apache-2.0	3.1M	Fine-tune one like it →Fine-tune one →
13	indonesian-roberta-base-posp-tagger	w11wo	Token classification	MIT	3.0M	Fine-tune one like it →Fine-tune one →
14	bart-large-mnli	facebook	Zero-shot classification	MIT	2.9M	Fine-tune one like it →Fine-tune one →
15	twitter-roberta-base-sentiment-latest	cardiffnlp	Text classification	CC BY 4.0	2.8M	Fine-tune one like it →Fine-tune one →
16	xlm-roberta-large	FacebookAI	Base encoders	MIT	2.8M	Fine-tune one like it →Fine-tune one →
17	deberta-v3-base	microsoft	Base encoders	MIT	2.7M	Fine-tune one like it →Fine-tune one →
18	roberta-base-go_emotions	SamLowe	Text classification	MIT	2.3M	Fine-tune one like it →Fine-tune one →
19	Bio_ClinicalBERT	emilyalsentzer	Base encoders	MIT	2.2M	Fine-tune one like it →Fine-tune one →
20	xlm-roberta-large-xnli	joeddav	Zero-shot classification	MIT	2.0M	Fine-tune one like it →Fine-tune one →
21	bert-base-multilingual-cased	google-bert	Base encoders	Apache-2.0	1.7M	Fine-tune one like it →Fine-tune one →
22	distilroberta-base	distilbert	Base encoders	Apache-2.0	1.5M	Fine-tune one like it →Fine-tune one →
23	bert-base-NER	dslim	Token classification	MIT	1.5M	Fine-tune one like it →Fine-tune one →
24	stanford-deidentifier-base	StanfordAIMI	Token classification	MIT	1.4M	Fine-tune one like it →Fine-tune one →
25	finbert-tone	yiyanghkust	Text classification	-	1.2M

New releases

New text classification and extraction models in the top 5,000

Uploaded to Hugging Face in the last six months with at least 25 likes or a trending score of 10, ranked by downloads over the last 30 days. Most format conversions and re-uploads are left out.

privacy-filteropenaiToken classification · uploaded Apr 17, 2026351K downloads in 30 daysFine-tune one like it →Fine-tune one →

gliner2.5-multi-v1fastinoToken classification · uploaded Aug 14, 2026282K downloads in 30 daysFine-tune one like it →Fine-tune one →

decider-2bMapikaText classification · uploaded Sep 16, 2026266K downloads in 30 daysFine-tune one like it →Fine-tune one →

gliner2-privacy-filter-PII-multifastinoToken classification · uploaded May 10, 2026190K downloads in 30 daysFine-tune one like it →Fine-tune one →

privacy-filter-nemotron-v2OpenMedToken classification · uploaded May 3, 202680K downloads in 30 daysFine-tune one like it →Fine-tune one →

vonwfzyxZero-shot classification · uploaded Sep 19, 202678K downloads in 30 daysFine-tune one like it →Fine-tune one →

What they're used for

Downloads by task

Share of downloads of text classification and extraction models in Hugging Face's top 5,000 on Oct 2, 2026, leaving out most format conversions and re-uploads.

Base encoders55.8%

Token classification22.3%

Text classification16.8%

Zero-shot classification4.0%

Question answering1.1%

Who's winning

Share of downloads by maker

Each repo counts under the account that uploaded it, leaving out most format conversions and re-uploads. Change is in percentage points since Jul 4, 2026.

google-bert22.8% (−4.6 pts)

OpenMed15.2% (+5.2 pts)

FacebookAI14.5% (−3.8 pts)

distilbert6.0% (+0.4 pts)

microsoft5.6% (+1.7 pts)

answerdotai2.2% (−2.6 pts)

ProsusAI2.0% (−0.6 pts)

cardiffnlp1.9% (−0.2 pts)

Other29.9% (+4.6 pts)

Licences of the most-downloaded text classification and extraction models

Apache-2.0 51.3%MIT 33.0%Llama licence 1.6%Other or none 14.2%

As declared on each repo, leaving out most format conversions and re-uploads.