Ruri v3 70M measured on 7 of 194 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
79.5JMTEB v2
Apr 2025released
384Dimensions
8K tokensMax input
jaLanguages
Alternatives?
ModelScoreCostPriceWhat changes
cBetterF2LLM v2 14BunstatedOpen+12%——Memory (4-bit): 0 GB → 8.4 GBcOpenF2LLM v2 8Bunstated+11%——Memory (4-bit): 0 GB → 4.5 GBcBetterF2LLM v2 4BunstatedOpen+10%——Memory (4-bit): 0 GB → 2.4 GBcBetterF2LLM v2 1.7BunstatedOpen+7%——Memory (4-bit): 0 GB → 1 GBsBetterSarashina Embedding v2 1BOpen+4%——Memory (4-bit): 0 GB → 0.7 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
cF2LLM v2 14BunstatedOpen+12%——Memory (4-bit): 0 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+11%——Memory (4-bit): 0 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+10%——Memory (4-bit): 0 GB → 2.4 GBcF2LLM v2 1.7BunstatedOpen+7%——Memory (4-bit): 0 GB → 1 GBsSarashina Embedding v2 1BOpen+4%——Memory (4-bit): 0 GB → 0.7 GBModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen+11%——Memory (4-bit): 0 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+10%——Memory (4-bit): 0 GB → 2.4 GBcF2LLM v2 1.7BunstatedOpen+7%——Memory (4-bit): 0 GB → 1 GBsSarashina Embedding v2 1BOpen+4%——Memory (4-bit): 0 GB → 0.7 GBcF2LLM v2 0.6BunstatedOpen+3%——Memory (4-bit): 0 GB → 0.4 GBModelScoreCostPriceWhat changes
cRuri v3 310MOpen+3%——Memory (4-bit): 0 GB → 0.2 GBcRuri v3 130MOpen+2%——Memory (4-bit): 0 GB → 0.1 GBcRuri Large v2Open-2%——Max input: 8K tokens → 1K tokens+1cRuri v3 30MOpen-2%——cRuri Base v2Open-3%——Max input: 8K tokens → 1K tokens+1cRuri LargeOpen-4%——Max input: 8K tokens → 1K tokens+1cRuri BaseOpen-7%——Max input: 8K tokens → 1K tokens+1All 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 · Japanese79.5#53
FAQ
How much does Ruri v3 70M cost?›
There is no per-unit API price: self-host only.
Is Ruri v3 70M free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ruri v3 70M, and what is it best at?›
#51 of 168 in Embeddings.
Is Ruri v3 70M better than F2LLM v2 330M?›
On JMTEB v2 · Mean over tasks · Japanese, Ruri v3 70M scores 70.6 vs 70.8 — about the same.
When was Ruri v3 70M released? Is there a newer version?›
Released 2025-04-09. It is the current version in its line.
Is Ruri v3 70M open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Ruri v3 70M locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Ruri v3 70M?›
Ruri v3 70M is an open-weights embeddings & retrieval model from cl-nagoya, released Apr 2025.
What are the best alternatives to Ruri v3 70M?›
F2LLM v2 14B (better), F2LLM v2 8B (open weights).