Dinov2 Giant measured on 18 of 203 Multimodal benchmarks18
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
17.7MIEB lite
Jul 2023released
1,536Dimensions
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
QEVA02 CLIP B 16unstatedOpen+13%——Memory (4-bit): 0.7 GB → 3 GBlCLIP ViT L 14 DataComp.XL S13B B90KOpen+6%——Run it yourself
estimateFits 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
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Dinov2 Giant cost?›
There is no per-unit API price: self-host only.
Is Dinov2 Giant free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Dinov2 Giant, and what is it best at?›
#54 of 56 in Multimodal.
Is Dinov2 Giant better than CLIP ViT B 16 DataComp.XL S13B B90K?›
On MIEB English · Image Clustering · English, Dinov2 Giant scores 81.4 vs 81.7 — about the same.
When was Dinov2 Giant released? Is there a newer version?›
Released 2023-07-18. It is the current version in its line.
Is Dinov2 Giant open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Dinov2 Giant locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Dinov2 Giant?›
Dinov2 Giant is an open-weights embeddings & retrieval model from Meta, released Jul 2023.
What are the best alternatives to Dinov2 Giant?›
Jina Embeddings v5 Omni Small (better), EVA02 CLIP B 16 (open weights).