Smallest ViT from Meta's DINOv3 family, a self-supervised backbone whose dense patch features transfer to many vision tasks without fine-tuning.
facebook/vjepa2-vitl-fpc64-256
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelVision encoder326M paramsEst. Edge GPUEstimated minimum compute for inference: Jetson Orin class, 8–16 GB shared memory. Not a benchmark.MIT
About
Meta's self-supervised ViT-L video encoder, pretrained by predicting masked video regions in latent space rather than in pixels.
Why it matters for physical AI
Its larger ViT-g sibling is the frozen backbone of Meta's action-conditioned V-JEPA 2-AC planner; this ViT-L checkpoint is a lighter, strong general video encoder for robot perception.
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.
hf download facebook/vjepa2-vitl-fpc64-256Uses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
Are video world models ready for robot planning?
V-JEPA 2 plans in a learned latent space, while Cosmos generates future video that can stand in for rollouts or synthetic training data.