Vjepa2 Vitg Fpc32 384 Diving48

Jun 2025
Older versionReplace withNo current replacement found yet.
Vjepa2 Vitg Fpc32 384 Diving48
Compare in
on
price not verifiedprice
—main score
Jun 2025released
1,408Dimensions

Ranking?

Retired models are left out of the current rankings.

Alternatives?

ModelScoreCostPriceWhat changes
Nothing here yet.

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use

Benchmarks

all categories
Embeddings & Retrieval
MVEB text video v1 · Video Clustering · English5.4
MVEB text video v1 · Video Classification · multilingual (16 languages)30.6
MVEB text video v1 · Video Pair Classification · English68.6
MVEB video v1 · Mean over tasks · multilingual (16 languages)46.2
MVEB video v1 · Mean over task types · multilingual (16 languages)50.3
MVEB video v1 · Video Classification · multilingual (16 languages)38
MVEB video v1 · Video Pair Classification · English62.5

FAQ

How much does Vjepa2 Vitg Fpc32 384 Diving48 cost?›

There is no per-unit API price: price not verified.

When was Vjepa2 Vitg Fpc32 384 Diving48 released? Is there a newer version?›

Released 2025-06-13. It is retired.

Is Vjepa2 Vitg Fpc32 384 Diving48 open source?›

Yes, the weights are open (MIT licence).

Can I run Vjepa2 Vitg Fpc32 384 Diving48 locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is Vjepa2 Vitg Fpc32 384 Diving48?›

Vjepa2 Vitg Fpc32 384 Diving48 is an open-weights embeddings & retrieval model from Meta, released Jun 2025.