Project AURIONAI Use-Cases Research & Innovation
visionfamily

DeiT

Meta data-efficient image transformers trained on ImageNet alone with distillation through attention.

MetaMetaUSA
Meta
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released23 Dec 2020
Opennessunknown
Runs onmobile or NPU
Statusactive

Lineage

2020202120222023DeiT-B distilledDeiT-B distilled, Dec 2020DeiT-Ti, Dec 2020DeiT IIIDeiT III, Apr 2022
MetaDeiT III belongs to this familyvision14 Apr 2022
MetaDeiT-B distilled belongs to this familyvision23 Dec 2020
MetaDeiT-Ti belongs to this familyvision23 Dec 20205.72M
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Image classification backbone architectures (CNN and vision transformer)produced by

Identity

Developer
Meta
Family
not in the notes
Released
23 Dec 2020 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
DeiT Ti, S, B (with distillation token) and DeiT III.
Context length
not in the notes
Input
image
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU
Footprint
Edge or toolkit builds listed in: TI edge AI model zoo.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2012.12877 https://arxiv.org/abs/2012.12877
  2. jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
  3. huggingface.co/facebook/deit-base-distilled-patch16-224 https://huggingface.co/facebook/deit-base-distilled-patch16-224
  4. github.com/TexasInstruments/edgeai-tensorlab/tree/main/e... https://github.com/TexasInstruments/edgeai-tensorlab/tree/main/edgeai-modelzoo/models/vision/classification/imagenet1k
  5. huggingface.co/api/models?pipeline_tag=image-classification&... https://huggingface.co/api/models?pipeline_tag=image-classification&sort=downloads&limit=50
  6. huggingface.co/timm/deit_tiny_patch16_224.fb_in1k https://huggingface.co/timm/deit_tiny_patch16_224.fb_in1k
  7. kaggle.com/models/keras/deit https://www.kaggle.com/models/keras/deit

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DeiT", https://aurion.semai.id/models/meta-deit/, records of October 2026.