Ruri v3 130M measured on 7 of 261 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
78.7JMTEB v2
Apr 2025released
512Dimensions
8K tokensMax input
jaLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+8%—$0.002Max input: 8K tokens → 2K tokens+2NOpenJa Embed Sts+9%——Max input: 8K tokens → 1K tokens+1iBetterMultilingual E5 Large InstructunstatedOpen+5%—$0.01Max input: 8K tokens → 1K tokens+1iBetterMultilingual E5 LargeunstatedOpen+3%—$0.01Max input: 8K tokens → 1K tokens+1iBetterE5 Mistral 7B InstructunstatedOpen+6%—$0.022Memory (4-bit): 0.1 GB → 4.3 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+8%—$0.002Max input: 8K tokens → 2K tokens+2iMultilingual E5 Large InstructunstatedOpen+5%—$0.01Max input: 8K tokens → 1K tokens+1iMultilingual E5 LargeunstatedOpen+3%—$0.01Max input: 8K tokens → 1K tokens+1iE5 Mistral 7B InstructunstatedOpen+6%—$0.022Memory (4-bit): 0.1 GB → 4.3 GB
Text Embedding 3 Largeunstated+5%—$0.13Languages: not verifiedModelScoreCostPriceWhat changes
NJa Embed StsOpen+9%——Max input: 8K tokens → 1K tokens+1cF2LLM v2 8BunstatedOpen+9%——Memory (4-bit): 0.1 GB → 4.5 GB
Harrier OSS v1 0.6BunstatedOpen+8%——Memory (4-bit): 0.1 GB → 0.4 GBcF2LLM v2 4BunstatedOpen+8%——Memory (4-bit): 0.1 GB → 2.4 GBEmbeddingGemma 300MunstatedOpen+8%—$0.002Max input: 8K tokens → 2K tokens+2ModelScoreCostPriceWhat changes
cRuri Large v2Open+6%——Max input: 8K tokens → 1K tokens+1cRuri LargeOpen+6%——Max input: 8K tokens → 1K tokens+1cRuri BaseOpen+6%——Max input: 8K tokens → 1K tokenscRuri Base v2Open+6%——Max input: 8K tokens → 1K tokenscRuri v3 30MOpen+4%——cRuri v3 310MOpen+3%——Memory (4-bit): 0.1 GB → 0.2 GBcRuri v3 70MOpensame——All 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 · Japanese78.7#55
FAQ
How much does Ruri v3 130M cost?›
There is no per-unit API price: self-host only.
Is Ruri v3 130M free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ruri v3 130M, and what is it best at?›
#55 of 164 in Embeddings.
Is Ruri v3 130M better than Gte Qwen2 1.5B Instruct?›
On JMTEB v2 · STS · Japanese, Ruri v3 130M scores 78.7 vs 78.8 — about the same.
When was Ruri v3 130M released? Is there a newer version?›
Released 2025-04-09. It is the current version in its line.
Is Ruri v3 130M open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Ruri v3 130M locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Ruri v3 130M?›
Ruri v3 130M is an open-weights embeddings & retrieval model from cl-nagoya, released Apr 2025.
What are the best alternatives to Ruri v3 130M?›
EmbeddingGemma 300M (better), Ja Embed Sts (open weights).