1,226 models · 1,226 open weights · 200 API-only · refreshed nightly

Open-weights models

Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.

All 1,426 Open weights (self-host) 1,226 API-only 200

All text-generation 534 text-to-image 155 image-text-to-text 112 ASR 86 sentence-similarity 64 translation 56 text-classification 51 feature-extraction 48 image-classification 39 token-classification 21 text-to-speech 19 audio-classification 12 image-segmentation 11 summarization 8 object-detection 8 audio-text-to-text 1 any-to-any 1

Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB

21 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	indonesian-roberta-base-posp-tagger w11wo · token-classification Open weights	120 M	512	✓ mit	3.4 M	from 1.1 GB
02	stanford-deidentifier-base StanfordAIMI · token-classification Open weights	—	512	✓ mit	1.4 M	—
03	bert-base-NER dslim · token-classification Open weights	110 M	512	✓ mit	1.1 M	from 1.0 GB
04	bert-large-cased-finetuned-conll03-english dbmdz · token-classification Open weights	330 M	512	unknown	737 K	from 2.0 GB
05	llmlingua-2-bert-base-multilingual-cased-meetingbank microsoft · token-classification Open weights	180 M	512	✓ apache-2.0	618 K	from 1.3 GB
06	punctuate-all kredor · token-classification Open weights	—	512	✓ mit	595 K	—
07	wikineural-multilingual-ner Babelscape · token-classification Open weights	180 M	512	✗ cc-by-nc-sa-4.0	583 K	from 1.3 GB
08	sat-3l-sm segment-any-text · token-classification Open weights	210 M	514	✓ mit	474 K	from 1.5 GB
09	deid_roberta_i2b2 obi · token-classification Open weights	350 M	512	✓ mit	352 K	from 2.1 GB
10	bert-small-pii-detection gravitee-io · token-classification Open weights	30 M	512	✓ apache-2.0	342 K	from 0.6 GB
11	ner-english flair · token-classification Open weights	—	—	unknown	272 K	—
12	CodonTransformer adibvafa · token-classification Open weights	90 M	4 K	✓ apache-2.0	270 K	from 0.9 GB
13	fullstop-punctuation-multilang-large oliverguhr · token-classification Open weights	560 M	512	✓ mit	269 K	from 3.0 GB
14	gliner2.5-multi-v1 fastino · token-classification Open weights	287 M	—	✓ apache-2.0	266 K	from 1.8 GB
15	ner-english-fast flair · token-classification Open weights	—	—	unknown	259 K	—
16	OpenMed-NER-PharmaDetect-SuperClinical-434M OpenMed · token-classification Open weights	430 M	512	✓ apache-2.0	250 K	from 1.5 GB
17	xlm-roberta-large-ner-hrl Davlan · token-classification Open weights	560 M	512	✓ afl-3.0	246 K	from 3.0 GB
18	privacy-filter openai · token-classification Open weights	1.4 B	131 K	✓ apache-2.0	212 K	from 6.9 GB
19	OpenMed-NER-ChemicalDetect-ModernMed-149M OpenMed · token-classification Open weights	150 M	8 K	✓ apache-2.0	212 K	from 0.9 GB
20	OpenMed-NER-BloodCancerDetect-TinyMed-65M OpenMed · token-classification Open weights	65 M	512	✓ apache-2.0	210 K	from 0.7 GB
21	OpenMed-NER-PharmaDetect-BigMed-278M OpenMed · token-classification Open weights	278 M	512	✓ apache-2.0	209 K	from 1.2 GB

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.