Skip to content

On-device models

Models you can run on iPhone, iPad and Mac, from Hugging Face

Core ML and MLX models published on Hugging Face, plus the models Apple publishes there, sorted by downloads in the last 30 days. Core ML models run on iPhone, iPad and Mac through Apple's Core ML framework; MLX models are made for Apple's MLX library, mostly on Apple silicon Macs (MLX Swift also runs on iPhone and iPad). Each name links to the model's page on Hugging Face.

1,009 Core ML models, 1,693 MLX models and 143 from Apple, updated daily from Hugging Face's public API. Last updated 2026-11-02 (UTC).

New this month

The most liked models created in the last 30 days, across Core ML, MLX and Apple's own.

See all new models

Showing 30 of 30.

ModelTaskSizeDownloads (30 days)
jinaai/jina-embeddings-v2-small-enCore MLEmbedding523 MB1.3M
jinaai/jina-embeddings-v2-base-enCore MLEmbedding2.2 GB357K
unum-cloud/uform3-image-text-multilingual-baseCore MLEmbedding2 GB6,177
FluidInference/embeddinggemma-2-coremlCore MLfrom google/embeddinggemma-2Embedding—2,131
camstack/camstack-modelsCore MLEmbedding—1,626
unum-cloud/uform3-image-text-english-largeCore MLEmbedding—676
NateRunsA-LIST/alist-food-text-embedderCore MLfrom google/embeddinggemma-2Embedding—353
faxenoff/code-daemon-embed-v1Core MLfrom Alibaba-NLP/gte-modernbert-baseEmbedding—205
wolfram-pro/multilingual-e5-small-coremlCore MLfrom intfloat/multilingual-e5-smallEmbedding—157
DangerLabs/dm-jepa-1.5Core MLEmbedding—155
yodayo-ai/jina-embeddings-v2-small-en-stCore MLEmbedding—144
unum-cloud/uform3-image-text-english-smallCore MLEmbedding—124
OpenInfinity/embeddinggemma-2-coreml-int8Core MLfrom google/embeddinggemma-2Embedding—107
FluidInference/granite-embedding-30m-sparse-coremlCore MLfrom ibm-granite/granite-embedding-30m-sparseEmbedding—82
Arraasz/granite-embedding-small-english-r2-aneCore MLfrom ibm-granite/granite-embedding-small-english-r2Embedding—58
unum-cloud/uform3-image-text-english-baseCore MLEmbedding—58
characteragent/granite-embedding-97m-multilingual-r2-coremlCore MLfrom ibm-granite/granite-embedding-97m-multilingual-r2Embedding—54
Severian/embedCore MLEmbedding—50
haihengh/all-MiniLM-L6-v2-coremlCore MLEmbedding—47
H4RUming/embeddinggemma-2-coreml-textCore MLfrom google/embeddinggemma-2Embedding—44
Nemosine/embeddinggemma-2-text-coremlCore MLfrom google/embeddinggemma-2Embedding—41
DangerLabs/dm-jepa-1.5-coremlCore MLEmbedding—34
aufklarer/SpeechBrain-ECAPA-VoxCeleb-20M-CoreMLCore MLfrom speechbrain/spkrec-ecapa-voxcelebEmbedding—32
apocryphx/embeddinggemma-300m-qat-q4_0-coremlCore MLfrom google/embeddinggemma-300mEmbedding—29
JGKarlin/ohia-bge-m3-coremlCore MLfrom BAAI/bge-m3Embedding—23
Mannyking/embeddinggemma-2-text-270m-coremlCore MLfrom google/embeddinggemma-2Embedding—21
erjigit17/qwen3-embedding-0.6b-ane-coreml-8bitCore MLfrom neuradex/Qwen3-Embedding-0.6B-CoreML-ANEEmbedding—20
usama99athar/multilingual-embedders-onnx-coremlCore MLEmbedding—20
rankun203/granite-embedding-97m-multilingual-r2-coremlCore MLfrom ibm-granite/granite-embedding-97m-multilingual-r2Embedding—19
rankun203/granite-embedding-311m-multilingual-r2-coremlCore MLfrom ibm-granite/granite-embedding-311m-multilingual-r2Embedding—18

Browse by task

Pages for tasks with at least 5 models, across Core ML, MLX and Apple's own.

More on on-device models

How to run these

  • Core ML: add the .mlpackage to your Xcode project, or download a compiled model when the app first needs it, and load it with the Core ML framework. Some repos ship their own Swift package; the model card says which.
  • MLX: on a Mac with Apple silicon, the mlx-lm and mlx-audio Python packages load these by name; inside an app, MLX Swift runs them on Mac, iPhone and iPad. Mind the memory: in our test a 4-bit 0.5B model peaked at about 0.36 GB on a Mac; larger models need far more.
  • Apple's own: some are Core ML files ready for an app; others are research weights for PyTorch and need converting with coremltools first.

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.