Model release

V-JEPA 2 ViT-g/16 (384 px)

V-JEPA 2 ViT-g/16 (384 px) is an open-weight model release in the V-JEPA 2 family from Meta (FAIR)3 1, version 2 ViT-g/16, 384 resolution (vjepa2-vitg-fpc64-384), released Jun 11, 2025. Its weights can be downloaded by the public2 3 under the Apache License 2.0 (Hugging Face model card)1 2.

The 1-billion-parameter ViT-g/16 encoder from Meta's V-JEPA 2, in the version that takes 64-frame clips at 384-pixel resolution. It was pretrained with self-supervision on VideoMix22M, a mix of about 22 million video and image samples. Meta's action-conditioned V-JEPA 2-AC world model was post-trained from a ViT-g/16 V-JEPA 2 encoder.1 3 7

Model hub: Model card (Hugging Face) (external site: huggingface.co)
Repository: vjepa2 repository (external site: github.com)
License: LICENSE (MIT, repository) (external site: github.com)
Paper: V-JEPA 2 paper (arXiv 2506.09985) (external site: arxiv.org)

On AI on Hugging Face: facebook/vjepa2-vitg-fpc64-384

Last reviewedSep 29, 2026Entry updated Sep 29, 2026Documented release Jun 11, 2025

Availability and license

Overall availability

Public

Downloadable without gating from Hugging Face and as a direct checkpoint link in the repository README.2 3

Availability fact review: not separately recorded

Availability is separate from permission: read the license before using or redistributing.

MIT License (vjepa2 repository) (external site: github.com)4 3
Applies to: Code · SPDX MIT · on the rubric’s OSI-approved software-license list · fact-level rights review not recorded
Plain-language guide to the MIT License
Apache License 2.0 (Hugging Face model card) (external site: huggingface.co)1 2
Applies to: Weights · SPDX Apache-2.0 · on the rubric’s OSI-approved software-license list · fact-level rights review not recorded
Plain-language guide to the Apache License 2.0

The repository README says most of V-JEPA 2 is licensed under MIT, with three data-augmentation and worker-initialization files under Apache 2.0, but does not name a separate license for the checkpoints linked from the README. The Hugging Face card for this checkpoint declares Apache-2.0. Meta's announcement says the code and checkpoints are available for commercial and research applications.3 1 8

Component reuse rights

A readable or downloadable component is not automatically reusable. These indicators concern recorded license evidence, not system certification.

weights: Unknown — no complete fact-level rights review
code: Unknown — no complete fact-level rights review
data: Unknown — no complete fact-level rights review
documentation: Unknown — no complete fact-level rights review

No complete system-rights review is recorded for this release.

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.2. An editorial category, not a certification.

Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.2. Unknown means unassessed or insufficient evidence.

Public materials checklist for V-JEPA 2 ViT-g/16 (384 px)
Item	Status	Notes and evidence
WeightsCan the general public download the model parameters for this release?	Public	Ungated Hugging Face repository and direct download link.2 3
Inference codeIs code for running the model published?	Public	The repository provides PyTorch Hub loaders and a demo; the model card documents use with Hugging Face Transformers.3 1
Training codeIs the code used to train the model published?	Public	The repository publishes the V-JEPA 2 pretraining loop and launch commands, with pretraining and cooldown configurations for ViT-g/16 (including a 384-pixel cooldown).3 5
Training-data informationDoes the information cover provenance, scope, acquisition, selection, labeling, processing, and where data or alternatives can be obtained? Access alone does not establish completeness.	Unknown	Not assessed.
Training-data accessCan the training data be obtained? This is independent of information completeness and reuse rights; original unshareable data need not be downloadable.	Unknown	Not assessed.
Complete training pipelineIs the complete base-training and preprocessing pipeline published, including configuration? Fine-tuning code or an inference SDK alone is insufficient.	Unknown	Not assessed.
Legacy data assessment (v0.1)Historical assessment combining download access and disclosure. Preserved for traceability; excluded from the v0.2 tier calculation. See the new separate assessments above.	Partial	The paper lists VideoMix22M's components (Something-Something v2, Kinetics, HowTo100M, YT-Temporal-1B, and ImageNet) and says all sources are publicly available. The YT-Temporal-1B portion was filtered by retrieval-based curation; this review did not find the curated subset list published.7
Training recipeAre the training configuration and procedure documented in enough detail to follow?	Public	Pretraining and cooldown configuration files are published, and the paper documents pretraining hyperparameters in its appendix.5 7
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.	Public	The repository publishes attentive-probe evaluation code, evaluation configs for the ViT-g 384-pixel model (for example SSv2, Diving48, EPIC-KITCHENS-100, Kinetics-400, ImageNet-1k), and trained probe checkpoints.3 6

What it is useful for

The model card describes use as a video and image encoder for video classification, retrieval, and as the video encoder of vision-language models.1

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.

The README notes that the code depends on decord, which does not support macOS, and documents Python 3.12 environment setup; the model card documents loading with Transformers' AutoModel and AutoVideoProcessor.3 1

Organization context

Meta

Other releases in the V-JEPA 2 family

V-JEPA 2.1 ViT-G/16 (384 px)Model-disclosure tier (USASI rubric v0.2): Open-weight

V-JEPA 2 family overview

What this catalog does not know

Unknown means the sources reviewed for this record do not document it. It is not evidence that something does not exist.

Training-data information: unknown.
Training-data access: unknown.
Complete training pipeline: unknown.

Have a primary source? How to report a correction.

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

The model card identifies FAIR at Meta as the developer, and the code is published by Meta in the facebookresearch GitHub organization. Meta Platforms, Inc. has its principal executive offices in Menlo Park, California, per its Form 10-K.1 3 9

Assessed Sep 29, 2026

Sources

1.
facebook/vjepa2-vitg-fpc64-384 model card (external site: huggingface.co)
Meta (Hugging Face) · Model card · accessed Sep 29, 2026
2.
facebook/vjepa2-vitg-fpc64-384 (Hugging Face model metadata) (external site: huggingface.co)
Meta (Hugging Face) · Model card · accessed Sep 29, 2026
3.
facebookresearch/vjepa2 README (external site: github.com)
Meta (GitHub) · Repository · accessed Sep 29, 2026
4.
facebookresearch/vjepa2 LICENSE (MIT) (external site: github.com)
Meta (GitHub) · License · accessed Sep 29, 2026
5.
vjepa2 configs/train/vitg16 (external site: github.com)
Meta (GitHub) · Repository · accessed Sep 29, 2026
6.
vjepa2 configs/eval/vitg-384 (external site: github.com)
Meta (GitHub) · Repository · accessed Sep 29, 2026
7.
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning (arXiv 2506.09985, HTML) (external site: arxiv.org)
arXiv (Meta FAIR authors) · Paper · accessed Sep 29, 2026
8.
V-JEPA 2 announcement (Meta AI blog) (external site: ai.meta.com)
Meta · Announcement · published Jun 11, 2025 · accessed Sep 29, 2026
9.
Meta Platforms, Inc. Form 10-K for the fiscal year ended December 31, 2025 (external site: sec.gov)
Meta Platforms, Inc. (U.S. SEC filing) · Filing · published Jan 29, 2026 · accessed Sep 29, 2026

Email a correction Report a correction Edit this entry

This listing is not an endorsement, a safety assessment, or a federal approval.

Cite this page

APA style

USASI. (2026, September 29). V-JEPA 2 ViT-g/16 (384 px). United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/open/v-jepa-2-vitg-384/

BibTeX

@misc{usasi_v_jepa_2_vitg_384,
  author = {{USASI}},
  title = {V-JEPA 2 ViT-g/16 (384 px)},
  year = {2026},
  month = sep,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/open/v-jepa-2-vitg-384/}},
  note = {United States of America Superintelligence. Last updated 2026-09-29}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

For maintainers: a “Listed in USASI” badge

Links to this page. It says the entry is listed, not endorsed or rated. About the badge

Markdown (for a README)

[![Listed in the USASI catalog](https://unitedstatesofamericasuperintelligence.com/badges/listed.svg)](https://unitedstatesofamericasuperintelligence.com/open/v-jepa-2-vitg-384/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/open/v-jepa-2-vitg-384/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/listed.svg" alt="Listed in the USASI catalog" height="20"></a>