Sarashina Embedding v2 1B measured on 7 of 261 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
84.2JMTEB v2
Jul 2025released
1,792Dimensions
8K tokensMax input
jaLanguages
Alternatives?
ModelScoreCostPriceWhat changes
NOpenJa Embed Sts+2%——Max input: 8K tokens → 1K tokenscOpenF2LLM v2 8Bunstated+1%——Memory (4-bit): 0.7 GB → 4.5 GB
OpenHarrier OSS v1 0.6Bunstatedsame——cOpenF2LLM v2 4Bunstatedsame——Memory (4-bit): 0.7 GB → 2.4 GB
OpenEmbeddingGemma 300Munstatedsame—$0.002Max input: 8K tokens → 2K tokens+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
NJa Embed StsOpen+2%——Max input: 8K tokens → 1K tokenscF2LLM v2 8BunstatedOpen+1%——Memory (4-bit): 0.7 GB → 4.5 GBHarrier OSS v1 0.6BunstatedOpensame——cF2LLM v2 4BunstatedOpensame——Memory (4-bit): 0.7 GB → 2.4 GBEmbeddingGemma 300MunstatedOpensame—$0.002Max input: 8K tokens → 2K tokens+1Run 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
Licencehttps://huggingface.co/sbintuitions/sarashina-embedding-v2-1b/blob/main/LICENSEcommercial use with conditions
History
2 versionsBenchmarks
in Embeddings & RetrievalFAQ
How much does Sarashina Embedding v2 1B cost?›
There is no per-unit API price: self-host only.
Is Sarashina Embedding v2 1B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Sarashina Embedding v2 1B, and what is it best at?›
#8 of 164 in Embeddings.
Is Sarashina Embedding v2 1B better than F2LLM v2 1.7B?›
On JMTEB v2 · STS · Japanese, Sarashina Embedding v2 1B scores 84.2 vs 84.3 — about the same.
When was Sarashina Embedding v2 1B released? Is there a newer version?›
Released 2025-07-30. It is the current version in its line.
Is Sarashina Embedding v2 1B open source?›
Yes, the weights are open (https://huggingface.co/sbintuitions/sarashina-embedding-v2-1b/blob/main/LICENSE licence).
Can I run Sarashina Embedding v2 1B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Sarashina Embedding v2 1B?›
Sarashina Embedding v2 1B is an open-weights embeddings & retrieval model from sbintuitions, released Jul 2025.
What are the best alternatives to Sarashina Embedding v2 1B?›
Ja Embed Sts (open weights).