1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

Summarization models

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

All 1,423 Open weights (self-host) 1,213 API-only 210

All text-generation 735 text-to-image 165 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 text-to-speech 23 token-classification 22 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 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

9 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	bart-large-cnn facebook · summarization Open weights	410 M	1 K	✓ mit	1.1 M	from 2.3 GB
02	distilbart-cnn-12-6 sshleifer · summarization Open weights	—	1 K	✓ apache-2.0	317 K	—
03	long-t5-tglobal-base-sci-simplify pszemraj · summarization Open weights	248 M	—	✓ apache-2.0	221 K	from 1.6 GB
04	T5-base-10K-summarization yatharth97 · summarization Open weights	220 M	—	unknown	84 K	from 1.5 GB
05	bart-large-cnn-samsum philschmid · summarization Open weights	—	1 K	✓ mit	73 K	—
06	MEETING_SUMMARY knkarthick · summarization Open weights	410 M	1 K	✓ apache-2.0	61 K	from 2.3 GB
07	pegasus-xsum google · summarization Open weights	—	512	unknown	54 K	—
08	financial-summarization-pegasus human-centered-summarization · summarization Open weights	570 M	512	unknown	52 K	from 3.1 GB
09	distilbart-xsum-12-6 sshleifer · summarization Open weights	—	1 K	✓ apache-2.0	45 K	—

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.