Ruri v3 310M measured on 7 of 261 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
80.8JMTEB v2
Apr 2025released
768Dimensions
8K tokensMax input
jaLanguages
Alternatives?
ModelScoreCostPriceWhat changes
sBetterComsat Embed Ja 8B PreviewOpen+7%——Memory (4-bit): 0.2 GB → 4.5 GBcBetterF2LLM v2 14BunstatedOpen+4%——Memory (4-bit): 0.2 GB → 8.4 GBcBetterF2LLM v2 8BunstatedOpen+3%——Memory (4-bit): 0.2 GB → 4.5 GBsOpenComsat Embed Ja 0.3B Preview+2%——cOpenF2LLM v2 4Bunstatedsame——Memory (4-bit): 0.2 GB → 2.4 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
sComsat Embed Ja 8B PreviewOpen+7%——Memory (4-bit): 0.2 GB → 4.5 GBcF2LLM v2 14BunstatedOpen+4%——Memory (4-bit): 0.2 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+3%——Memory (4-bit): 0.2 GB → 4.5 GBModelScoreCostPriceWhat changes
sComsat Embed Ja 8B PreviewOpen+7%——Memory (4-bit): 0.2 GB → 4.5 GBcF2LLM v2 8BunstatedOpen+3%——Memory (4-bit): 0.2 GB → 4.5 GBsComsat Embed Ja 0.3B PreviewOpen+2%——cF2LLM v2 4BunstatedOpensame——Memory (4-bit): 0.2 GB → 2.4 GBsSarashina Embedding v2 1BOpensame——Memory (4-bit): 0.2 GB → 0.7 GBModelScoreCostPriceWhat changes
cRuri v3 130MOpensame——cRuri v3 70MOpen-2%——cRuri v3 30MOpen-4%——cRuri Large v2Open-5%——Max input: 8K tokens → 1K tokenscRuri Base v2Open-8%——Max input: 8K tokens → 1K tokenscRuri LargeOpen-10%——Max input: 8K tokens → 1K tokenscRuri BaseOpen-14%——Max input: 8K tokens → 1K tokensAll 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
Benchmarks
in Embeddings & RetrievalJMTEB v2 · STS · Japanese80.8#33
FAQ
How much does Ruri v3 310M cost?›
There is no per-unit API price: self-host only.
Is Ruri v3 310M free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ruri v3 310M, and what is it best at?›
#33 of 164 in Embeddings.
Is Ruri v3 310M better than Ruri v3 130M?›
On JMTEB v2 · Retrieval · Japanese, Ruri v3 310M scores 76.3 vs 76.4 — about the same.
When was Ruri v3 310M released? Is there a newer version?›
Released 2025-04-09. It is the current version in its line.
Is Ruri v3 310M open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Ruri v3 310M locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Ruri v3 310M?›
Ruri v3 310M is an open-weights embeddings & retrieval model from cl-nagoya, released Apr 2025.
What are the best alternatives to Ruri v3 310M?›
Comsat Embed Ja 8B Preview (better).