Nb Sbert Base measured on 6 of 261 Embeddings benchmarks6
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
72MTEB Scandinavian v1
Nov 2022released
768Dimensions
0K tokensMax input
NorwegianLanguages
Alternatives?
ModelScoreCostPriceWhat changes
iBetterMultilingual E5 Large InstructunstatedOpen+34%—$0.01Memory (4-bit): 0.1 GB → 0.3 GBSOpenSFR Embedding 2 Runstated+42%——Memory (4-bit): 0.1 GB → 4.3 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
iMultilingual E5 Large InstructunstatedOpen+34%—$0.01Memory (4-bit): 0.1 GB → 0.3 GBModelScoreCostPriceWhat changes
SSFR Embedding 2 RunstatedOpen+42%——Memory (4-bit): 0.1 GB → 4.3 GBcF2LLM v2 8BunstatedOpen+41%——Memory (4-bit): 0.1 GB → 4.5 GBiE5 Mistral 7B InstructunstatedOpen+38%—$0.022Memory (4-bit): 0.1 GB → 4.3 GBGGritLM 7BunstatedOpen+38%——Languages: not verified+1SSFR Embedding MistralunstatedOpen+37%——Memory (4-bit): 0.1 GB → 4.3 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 Nb Sbert Base cost?›
There is no per-unit API price: price not verified.
How good is Nb Sbert Base, and what is it best at?›
#28 of 205 in Embeddings.
Is Nb Sbert Base better than Granite Embedding 278M Multilingual?›
On MTEB Scandinavian v1 · Clustering · multilingual (2 languages), Nb Sbert Base scores 37.2 vs 37.6 — about the same.
When was Nb Sbert Base released? Is there a newer version?›
Released 2022-11-23. It is the current version in its line.
Is Nb Sbert Base open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Nb Sbert Base locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Nb Sbert Base?›
Nb Sbert Base is an open-weights embeddings & retrieval model from NbAiLab, released Nov 2022.
What are the best alternatives to Nb Sbert Base?›
Multilingual E5 Large Instruct (better), SFR Embedding 2 R (open weights).