DenseOn measured on 3 of 261 Embeddings benchmarks3
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
56.2BEIR
Apr 2026released
768Dimensions
1K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
lmLateOnOpen+2%——Memory (4-bit): 0.1 GB → 0.2 GBlLateOnOpen+2%——Max input: 1K tokens → 0K tokenslmDenseOnOpensame——Memory (4-bit): 0.1 GB → 0.2 GBlColBERT ZeroOpensame——lGTE ModernColBERT v1Open-3%——Max input: 1K tokens → 0K tokenslColBERT Zero SupervisedOpen-8%——lColBERT Zero UnsupervisedOpen-9%——Max input: 1K tokens → 0K tokenslDenseOn UnsupervisedOpen-13%——All lightonai models →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 & RetrievalBEIR · Retrieval · English56.2#32
FAQ
How much does DenseOn cost?›
There is no per-unit API price: price not verified.
How good is DenseOn, and what is it best at?›
#32 of 194 in Embeddings.
Is DenseOn better than Gte Qwen1.5 7B Instruct?›
On BEIR · Mean over tasks · English, DenseOn scores 56.2 vs 56.2 — about the same.
When was DenseOn released? Is there a newer version?›
Released 2026-04-21. It is the current version in its line.
Is DenseOn open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run DenseOn locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is DenseOn?›
DenseOn is an open-weights embeddings & retrieval model from lightonai, released Apr 2026.
What are the best alternatives to DenseOn?›
Qwen 3 Embedding 8B (better), NV Embed v2 (open weights).