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

8 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	locate-anything.cpp-gguf mudler · object-detection Open weights	3.8 B	—	other	8.3 M	from 6.3 GB
02	table-transformer-structure-recognition microsoft · object-detection Open weights	30 M	1 K	✓ mit	1.3 M	from 0.6 GB
03	rtdetr_r101vd_coco_o365 PekingU · object-detection Open weights	80 M	—	✓ apache-2.0	1.2 M	from 0.9 GB
04	PP-DocLayoutV3_safetensors PaddlePaddle · object-detection Open weights	33 M	—	✓ apache-2.0	922 K	from 0.7 GB
05	yolos-small hustvl · object-detection Open weights	30 M	—	✓ apache-2.0	697 K	from 0.6 GB
06	table-transformer-detection microsoft · object-detection Open weights	30 M	1 K	✓ mit	328 K	from 0.6 GB
07	rtdetr_v2_r18vd PekingU · object-detection Open weights	20 M	—	✓ apache-2.0	290 K	from 0.6 GB
08	yolov8m-table-extraction keremberke · object-detection Open weights	8.0 M	—	agpl-3.0	191 K	from 0.5 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.