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
BetterEmbeddingGemma 300MunstatedOpen+3%—$0.002Max input: 8K tokens → 2K tokens+1cOpenF2LLM v2 8Bunstated+17%——Memory (4-bit): 0.7 GB → 4.5 GBcBetterF2LLM v2 14BunstatedOpen+17%——Memory (4-bit): 0.7 GB → 8.4 GBcBetterF2LLM v2 4BunstatedOpen+16%——Memory (4-bit): 0.7 GB → 2.4 GBcBetterF2LLM v2 1.7BunstatedOpen+15%——Memory (4-bit): 0.7 GB → 1 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+3%—$0.002Max input: 8K tokens → 2K tokens+1cF2LLM v2 14BunstatedOpen+17%——Memory (4-bit): 0.7 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+17%——Memory (4-bit): 0.7 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+16%——Memory (4-bit): 0.7 GB → 2.4 GBcF2LLM v2 1.7BunstatedOpen+15%——Memory (4-bit): 0.7 GB → 1 GBRun 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 160M?›
On JMTEB v2 · Classification · Japanese, Sarashina Embedding v2 1B scores 69.6 vs 70.6 — lower.
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?›
EmbeddingGemma 300M (better), F2LLM v2 8B (open weights).