Skip to content

All on-device models

Image classification models for iPhone and Mac (Core ML & MLX)

33 models for this task are tagged Core ML or MLX on Hugging Face, or come from Apple: 22 Core ML, 1 MLX and 10 other Apple models. The table lists the most downloaded in the last 30 days.

Last updated 2026-11-02 (UTC).

Showing 33 of 33.

ModelSizeDownloads (30 days)
apple/mobilevit-xx-smallCore ML16.1 MB32.5K
apple/mobilevit-smallCore ML67.8 MB7,331
apple/mobilevitv2-1.0-imagenet1k-256Apple, other format—2,862
apple/mobileclip_s0_timmApple, other format—1,598
julien-c/hotdog-not-hotdogCore ML—749
apple/mobilevit-x-smallCore ML—478
apple/mobileclip_s2_timmApple, other format—371
apple/mobileclip_b_timmApple, other format—320
apple/mobileclip_s1_timmApple, other format—312
flyswot/convnext-tiny-224_flyswotCore ML—226
apple/mobileclip_b_lt_timmApple, other format—207
apple/coreml-resnet-50Core ML—164
grdesignbuild/volleyball-jersey-number-readerCore MLfrom microsoft/resnet-18—70
Matthijs/mobilenet_v2_1.4_224Core ML—63
apple/AIM-600MApple, other format—60
phyloforfun/lm3_ruler_classifier_ensemble__yolo26x_cls_224Core ML—58
apple/AIM-7BApple, other format—51
phyloforfun/lm3_ruler_classifier_ensemble__yolo26n_cls_224Core ML—49
rociiu/yolo-go-stone-classifierCore ML—46
apple/coreml-FastViT-T8Core ML—44
InspiratioNULL/image-safety-classifier-s-CoreMLCore ML—40
apple/AIM-1BApple, other format—38
ortusai/rightwayupCore MLfrom timm/vit_large_patch14_dinov2.lvd142m—38
apple/AIM-3BApple, other format—37
NimaBoscarino/efficientformer-l7-300Core ML—35
apple/coreml-FastViT-MA36Core ML—20
c2p-cmd/PetsImageClassifierCore ML—18
mickeyvanolst/yolo-coremlCore ML—18
NimaBoscarino/efficientformer-l3-300Core ML—17
potnoodledev/noodles-not-noodlesCore ML—17
shafi-afridi/face-capture-qualityCore ML—17
Matthijs/mobilevit-smallCore ML—16
apple/AIMMLX—0

Reading the table

  • Downloads are Hugging Face's count for the last 30 days, not all time. Hugging Face counts requests for a model's main file, so one install can count more than once.
  • Size is the total of the repo's current files on Hugging Face, in the sizes it shows (1 GB = 1,000 MB). Some repos hold several variants of a model, so it can be larger than the one download you need; a dash means it has not been measured yet.
  • Trending is Hugging Face's own score for recent attention. "from" under a name is the model it was made from.
  • Parameters is the parameter count in the model files. A count marked * comes from the model's name (such as 27B) instead: the files gave none, or a much smaller one, as packed low-bit files can.
  • Quantization is read from the model's tags and name, not checked against the files.

Before you use one

The list comes from Hugging Face's public API and is updated daily. We don't test each model. Check the license and read the model card before you ship one in an app: some licenses limit commercial use, and "other" means the terms are on the model card. Models whose names or tags point at adult or safety-removed content are left out, and so are gated models that need a Hugging Face sign-in to download.

Other tasks