1,423 models · 1,213 open weights · 210 API-only · refreshed nightly
Image classification 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.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 01 | vit-base-patch16-224 | 90 M | — | ✓ apache-2.0 | 15.0 M | from 0.9 GB |
| 02 | mobilenetv3_small_100.lamb_in1k | 2.6 M | — | ✓ apache-2.0 | 12.7 M | from 0.5 GB |
| 03 | Gender-Classifier-Mini | 93 M | — | ✓ apache-2.0 | 8.1 M | from 1.7 GB |
| 04 | tf_efficientnetv2_s.in21k_ft_in1k | 20 M | — | ✓ apache-2.0 | 3.6 M | from 0.6 GB |
| 05 | resnet18.a1_in1k | 10 M | — | ✓ apache-2.0 | 2.0 M | from 0.6 GB |
| 06 | resnet50.a1_in1k | 30 M | — | ✓ apache-2.0 | 1.6 M | from 0.6 GB |
| 07 | nsfw_image_detection | 90 M | — | ✓ apache-2.0 | 1.6 M | from 0.9 GB |
| 08 | gender-classification | 90 M | — | unknown | 1.3 M | from 0.9 GB |
| 09 | efficientvit_l2.r288_in1k | 64 M | — | ✓ apache-2.0 | 1.3 M | from 0.8 GB |
| 10 | rorshark-vit-base | 90 M | — | ✓ apache-2.0 | 860 K | from 0.9 GB |
| 11 | wide_resnet50_2.racm_in1k | 70 M | — | ✓ apache-2.0 | 795 K | from 0.8 GB |
| 12 | resnet50.ram_in1k | 30 M | — | ✓ apache-2.0 | 709 K | from 0.6 GB |
| 13 | vit-base-nsfw-detector | 90 M | — | ✓ apache-2.0 | 707 K | from 0.9 GB |
| 14 | resnet34.a1_in1k | 20 M | — | ✓ apache-2.0 | 707 K | from 0.6 GB |
| 15 | nsfw-image-detection-384 | 5.6 M | — | ✓ apache-2.0 | 674 K | from 0.5 GB |
| 16 | convnext_tiny.in12k_ft_in1k | 30 M | — | ✓ apache-2.0 | 651 K | from 0.6 GB |
| 17 | repvgg_a0.rvgg_in1k | 10 M | — | ✓ mit | 608 K | from 0.5 GB |
| 18 | efficientnet_b0.ra_in1k | 10 M | — | ✓ apache-2.0 | 576 K | from 0.5 GB |
| 19 | nsfw_image_detector | 90 M | — | ✓ mit | 460 K | from 0.7 GB |
| 20 | vit_base_patch16_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 402 K | from 0.9 GB |
| 21 | swinv2-tiny-patch4-window16-256 | — | — | ✓ apache-2.0 | 390 K | — |
| 22 | MegaDescriptor-T-224 | — | — | ✗ cc-by-nc-4.0 | 380 K | — |
| 23 | AI-image-detector | — | — | ✓ cc-by-4.0 | 353 K | — |
| 24 | convnext_base.fb_in22k_ft_in1k | 90 M | — | ✓ apache-2.0 | 350 K | from 0.9 GB |
| 25 | wide_resnet101_2.tv_in1k | 127 M | — | ✓ bsd-3-clause | 350 K | from 1.1 GB |
| 26 | resnet-18 | 12 M | — | ✓ apache-2.0 | 333 K | from 0.6 GB |
| 27 | MegaDescriptor-B-224 | — | — | ✗ cc-by-nc-4.0 | 331 K | — |
| 28 | convnextv2_large.fcmae_ft_in22k_in1k_384 | 200 M | — | ✗ cc-by-nc-4.0 | 327 K | from 1.4 GB |
| 29 | regnety_032.ra_in1k | 20 M | — | ✓ apache-2.0 | 314 K | from 0.6 GB |
| 30 | vit_small_patch16_224.augreg_in21k_ft_in1k | 20 M | — | ✓ apache-2.0 | 302 K | from 0.6 GB |
| 31 | resnet50.fb_swsl_ig1b_ft_in1k | 26 M | — | ✗ cc-by-nc-4.0 | 288 K | from 0.6 GB |
| 32 | vit_base_patch8_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 279 K | from 0.9 GB |
| 33 | vit_tiny_patch16_224.augreg_in21k_ft_in1k | 10 M | — | ✓ apache-2.0 | 276 K | from 0.5 GB |
| 34 | convnext_tiny.fb_in22k_ft_in1k | 29 M | — | ✓ apache-2.0 | 275 K | from 0.6 GB |
| 35 | vit_tiny_r_s16_p8_224.augreg_in21k | 10 M | — | ✓ apache-2.0 | 274 K | from 0.5 GB |
| 36 | edgenext_small.usi_in1k | 10 M | — | ✓ mit | 271 K | from 0.5 GB |
| 37 | densenetblur121d.ra_in1k | 8.1 M | — | ✓ apache-2.0 | 262 K | from 0.5 GB |
| 38 | MegaDescriptor-L-384 | — | — | ✗ cc-by-nc-4.0 | 249 K | — |
| 39 | nsfw-classifier | 90 M | — | ✗ cc-by-nc-nd-4.0 | 236 K | from 0.9 GB |
| 40 | resnet18.a3_in1k | 10 M | — | ✓ apache-2.0 | 231 K | from 0.6 GB |
| 41 | resnet-50 | 30 M | — | ✓ apache-2.0 | 212 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.