Project AURIONAI Use-Cases Research & Innovation
Apple
vision

AIMv2

Apple vision encoders pretrained with multimodal autoregressive objectives, from the paper "Multimodal Autoregressive Pre-training of Large Vision Encoders".

AppleAppleUSAAIMFamily
Overview of the AIMv2 family of vision encoders with benchmark charts, from the model card.
Levelvariant
Classvision
Parameters309.2M
Contextnot in the notes
Released21 Nov 2024
Opennessopen weights restricted
Runs onnot in the notes
Statusactive

Lineage

successor
AIM to AIMv2: successor, high confidenceAIMAIMApple, Jan 2024AIMv2AIMv2Apple, Nov 2024
AppleAIM is the parent (successor)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Self-supervised visual representation learningproduced byContrastive image-text encoders (CLIP and SigLIP lines)produced by

Identity

Developer
Apple
Family
AIM
Released
21 Nov 2024 sourcesannouncement page
Weights published
29 Oct 2024
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
309.2M sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
Output
not in the notes
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
open weights restricted
Licence
not in the notes sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
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/2411.14402 https://arxiv.org/abs/2411.14402
  2. huggingface.co/apple/aimv2-large-patch14-224 https://huggingface.co/apple/aimv2-large-patch14-224

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "AIMv2", https://aurion.semai.id/models/apple-aimv2/, records of October 2026.