Ja Embed Sts measured on 7 of 261 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
85.6JMTEB v2
Sep 2026released
1,024Dimensions
1K tokensMax input
en, koLanguages
Alternatives?
ModelScoreCostPriceWhat changes
cBetterF2LLM v2 14BunstatedOpen+16%——Memory (4-bit): 0.2 GB → 8.4 GBcOpenF2LLM v2 8Bunstated+15%——Memory (4-bit): 0.2 GB → 4.5 GBcBetterF2LLM v2 4BunstatedOpen+13%——Memory (4-bit): 0.2 GB → 2.4 GBcBetterF2LLM v2 1.7BunstatedOpen+11%——Memory (4-bit): 0.2 GB → 1 GBsBetterSarashina Embedding v2 1BOpen+7%——Languages: loses en, ko+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
cF2LLM v2 14BunstatedOpen+16%——Memory (4-bit): 0.2 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+15%——Memory (4-bit): 0.2 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+13%——Memory (4-bit): 0.2 GB → 2.4 GBcF2LLM v2 1.7BunstatedOpen+11%——Memory (4-bit): 0.2 GB → 1 GBsSarashina Embedding v2 1BOpen+7%——Languages: loses en, ko+1ModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen+15%——Memory (4-bit): 0.2 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+13%——Memory (4-bit): 0.2 GB → 2.4 GBcF2LLM v2 1.7BunstatedOpen+11%——Memory (4-bit): 0.2 GB → 1 GBsSarashina Embedding v2 1BOpen+7%——Languages: loses en, ko+1cF2LLM v2 0.6BunstatedOpen+7%——Memory (4-bit): 0.2 GB → 0.4 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
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Ja Embed Sts cost?›
There is no per-unit API price: self-host only.
Is Ja Embed Sts free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ja Embed Sts, and what is it best at?›
#1 of 164 in Embeddings.
Is Ja Embed Sts better than Harrier OSS v1 270M?›
On JMTEB v2 · Mean over tasks · Japanese, Ja Embed Sts scores 68.3 vs 69.3 — about the same.
When was Ja Embed Sts released? Is there a newer version?›
Released 2026-09-15. It is the current version in its line.
Is Ja Embed Sts open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Ja Embed Sts locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Ja Embed Sts?›
Ja Embed Sts is an open-weights embeddings & retrieval model from NGA-KR, released Sep 2026.
What are the best alternatives to Ja Embed Sts?›
F2LLM v2 14B (better), F2LLM v2 8B (open weights).