Meta's self-supervised ViT-L video encoder, pretrained by predicting masked video regions in latent space rather than in pixels.
facebook/dinov3-vits16-pretrain-lvd1689m
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelVision encoder22M paramsEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.DINOv3 LicenseCustom or unstated terms. The upstream license governs use.GatedGated upstream: accept the owner's terms on Hugging Face to download.
About
Smallest ViT from Meta's DINOv3 family, a self-supervised backbone whose dense patch features transfer to many vision tasks without fine-tuning.
Why it matters for physical AI
A small frozen feature extractor that many robot policies and perception heads can build on.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
Gated upstream. Accept the owner's terms on Hugging Face and sign in with hf auth login before downloading.
hf download facebook/dinov3-vits16-pretrain-lvd1689mUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.