Ruri Base measured on 7 of 261 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
83.3JMTEB v2
Aug 2024released
768Dimensions
1K tokensMax input
jaLanguages
Alternatives?
ModelScoreCostPriceWhat changes
sBetterComsat Embed Ja 8B PreviewOpen+24%——Memory (4-bit): 0.1 GB → 4.5 GBcBetterF2LLM v2 14BunstatedOpen+21%——Memory (4-bit): 0.1 GB → 8.4 GBcBetterF2LLM v2 8BunstatedOpen+19%——Memory (4-bit): 0.1 GB → 4.5 GBsBetterComsat Embed Ja 0.3B PreviewOpen+18%——Memory (4-bit): 0.1 GB → 0.2 GBcBetterF2LLM v2 4BunstatedOpen+17%——Memory (4-bit): 0.1 GB → 2.4 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
sComsat Embed Ja 8B PreviewOpen+24%——Memory (4-bit): 0.1 GB → 4.5 GBcF2LLM v2 14BunstatedOpen+21%——Memory (4-bit): 0.1 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+19%——Memory (4-bit): 0.1 GB → 4.5 GBsComsat Embed Ja 0.3B PreviewOpen+18%——Memory (4-bit): 0.1 GB → 0.2 GBcF2LLM v2 4BunstatedOpen+17%——Memory (4-bit): 0.1 GB → 2.4 GBModelScoreCostPriceWhat changes
sComsat Embed Ja 8B PreviewOpen+24%——Memory (4-bit): 0.1 GB → 4.5 GBcF2LLM v2 8BunstatedOpen+19%——Memory (4-bit): 0.1 GB → 4.5 GBsComsat Embed Ja 0.3B PreviewOpen+18%——Memory (4-bit): 0.1 GB → 0.2 GBcF2LLM v2 4BunstatedOpen+17%——Memory (4-bit): 0.1 GB → 2.4 GBsSarashina Embedding v2 1BOpen+16%——Memory (4-bit): 0.1 GB → 0.7 GBModelScoreCostPriceWhat changes
cRuri v3 130MOpen+16%——cRuri v3 310MOpen+16%——Memory (4-bit): 0.1 GB → 0.2 GBcRuri v3 70MOpen+13%——cRuri v3 30MOpen+11%——cRuri Large v2Open+10%——Memory (4-bit): 0.1 GB → 0.2 GBcRuri Base v2Open+7%——cRuri LargeOpen+4%——Memory (4-bit): 0.1 GB → 0.2 GBAll cl-nagoya 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
History
2 versionsBenchmarks
in Embeddings & RetrievalJMTEB v2 · STS · Japanese83.3#16
FAQ
How much does Ruri Base cost?›
There is no per-unit API price: self-host only.
Is Ruri Base free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ruri Base, and what is it best at?›
#16 of 164 in Embeddings.
Is Ruri Base better than Bekko Embedding v1 A8m?›
On JMTEB v2 · Retrieval · Japanese, Ruri Base scores 65.9 vs 66.9 — lower.
When was Ruri Base released? Is there a newer version?›
Released 2024-08-28. It is the current version in its line.
Is Ruri Base open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Ruri Base locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Ruri Base?›
Ruri Base is an open-weights embeddings & retrieval model from cl-nagoya, released Aug 2024.
What are the best alternatives to Ruri Base?›
Comsat Embed Ja 8B Preview (better).