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.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 01 | mobilenetv3_small_100.lamb_in1k | <0.1 M | — | ✓ apache-2.0 | 17.0 M | from 0.5 GB |
| 02 | vit-base-patch16-224 | 90 M | — | ✓ apache-2.0 | 14.0 M | from 0.9 GB |
| 03 | Gender-Classifier-Mini | 93 M | — | ✓ apache-2.0 | 6.1 M | from 1.7 GB |
| 04 | resnet18.a1_in1k | 10 M | — | ✓ apache-2.0 | 2.0 M | from 0.6 GB |
| 05 | tf_efficientnetv2_s.in21k_ft_in1k | 20 M | — | ✓ apache-2.0 | 1.9 M | from 0.6 GB |
| 06 | nsfw_image_detection | 90 M | — | ✓ apache-2.0 | 1.6 M | from 0.9 GB |
| 07 | resnet50.a1_in1k | 30 M | — | ✓ apache-2.0 | 1.4 M | from 0.6 GB |
| 08 | gender-classification | 90 M | — | unknown | 1.3 M | from 0.9 GB |
| 09 | rorshark-vit-base | 90 M | — | ✓ apache-2.0 | 829 K | from 0.9 GB |
| 10 | resnet34.a1_in1k | 20 M | — | ✓ apache-2.0 | 752 K | from 0.6 GB |
| 11 | convnext_tiny.in12k_ft_in1k | 30 M | — | ✓ apache-2.0 | 735 K | from 0.6 GB |
| 12 | resnet-18 | 12 M | — | ✓ apache-2.0 | 728 K | from 0.6 GB |
| 13 | resnet50.ram_in1k | 30 M | — | ✓ apache-2.0 | 709 K | from 0.6 GB |
| 14 | wide_resnet50_2.racm_in1k | 70 M | — | ✓ apache-2.0 | 698 K | from 0.8 GB |
| 15 | vit-base-nsfw-detector | 90 M | — | ✓ apache-2.0 | 682 K | from 0.9 GB |
| 16 | efficientnet_b0.ra_in1k | 10 M | — | ✓ apache-2.0 | 673 K | from 0.5 GB |
| 17 | repvgg_a0.rvgg_in1k | 10 M | — | ✓ mit | 578 K | from 0.5 GB |
| 18 | vit_base_patch16_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 424 K | from 0.9 GB |
| 19 | nsfw-image-detection-384 | 5.6 M | — | ✓ apache-2.0 | 406 K | from 0.5 GB |
| 20 | swinv2-tiny-patch4-window16-256 | — | — | ✓ apache-2.0 | 372 K | — |
| 21 | AI-image-detector | — | — | ✓ cc-by-4.0 | 353 K | — |
| 22 | vit_small_patch16_224.augreg_in21k_ft_in1k | 20 M | — | ✓ apache-2.0 | 333 K | from 0.6 GB |
| 23 | nsfw_image_detector | 90 M | — | ✓ mit | 315 K | from 0.7 GB |
| 24 | MegaDescriptor-T-224 | — | — | ✗ cc-by-nc-4.0 | 288 K | — |
| 25 | convnextv2_large.fcmae_ft_in22k_in1k_384 | 200 M | — | ✗ cc-by-nc-4.0 | 280 K | from 1.4 GB |
| 26 | convnext_tiny.fb_in22k_ft_in1k | 29 M | — | ✓ apache-2.0 | 274 K | from 0.6 GB |
| 27 | vit_tiny_r_s16_p8_224.augreg_in21k | 10 M | — | ✓ apache-2.0 | 274 K | from 0.5 GB |
| 28 | resnet-50 | 30 M | — | ✓ apache-2.0 | 266 K | from 0.6 GB |
| 29 | fairface_age_image_detection | 90 M | — | ✓ apache-2.0 | 248 K | from 2.4 GB |
| 30 | plant-identity | 90 M | — | unknown | 245 K | from 0.9 GB |
| 31 | convnext_small.fb_in22k_ft_in1k_384 | 50 M | — | ✓ apache-2.0 | 243 K | from 0.7 GB |
| 32 | efficientnet_b3.ra2_in1k | 10 M | — | ✓ apache-2.0 | 242 K | from 0.6 GB |
| 33 | convnext_femto.d1_in1k | 10 M | — | ✓ apache-2.0 | 241 K | from 0.5 GB |
| 34 | mit-b2 | — | — | other | 240 K | — |
| 35 | CommunityForensics-DeepfakeDet-ViT | 20 M | — | ✓ mit | 240 K | from 0.9 GB |
| 36 | vit_base_patch8_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 238 K | from 0.9 GB |
| 37 | resnet18.a3_in1k | 10 M | — | ✓ apache-2.0 | 210 K | from 0.6 GB |
| 38 | MegaDescriptor-B-224 | — | — | ✗ cc-by-nc-4.0 | 208 K | — |
| 39 | densenet201.tv_in1k | 20 M | — | ✓ apache-2.0 | 198 K | from 0.6 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.