Dinov2 Large measured on 18 of 195 Multimodal benchmarks18
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
19.9MIEB lite
Jul 2023released
1,024Dimensions
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
LLCO Embedding Omni 7BunstatedOpen×4.1——Memory (4-bit): 0.2 GB → 5.4 GBLLCO Embedding Omni 3BunstatedOpen×4——Memory (4-bit): 0.2 GB → 2.8 GBHE5 Omni 7BunstatedOpen×3.9——Memory (4-bit): 0.2 GB → 5.4 GBRun 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 Large cost?›
There is no per-unit API price: self-host only.
Is Dinov2 Large free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Dinov2 Large, and what is it best at?›
#50 of 56 in Multimodal.
Is Dinov2 Large better than Blip2 Opt 2.7B?›
On MIEB lite · Visual semantic similarity (multilingual) · multilingual (13 languages), Dinov2 Large scores 19.9 vs 21.8 — lower.
When was Dinov2 Large released? Is there a newer version?›
Released 2023-07-18. It is the current version in its line.
Is Dinov2 Large open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Dinov2 Large locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Dinov2 Large?›
Dinov2 Large is an open-weights embeddings & retrieval model from Meta, released Jul 2023.
What are the best alternatives to Dinov2 Large?›
EmbeddingGemma 2 (better), LCO Embedding Omni 7B (open weights).