Octen Embedding 4B measured on 14 of 261 Embeddings benchmarks14
BenchmarkByScoreRank
Reranking9
Other5
No benchmark matches
self-host onlyprice
64.6RTEB French beta
Dec 2025released
2,560Dimensions
41K tokensMax input
en, zhLanguages
Alternatives?
ModelScoreCostPriceWhat changes
VBetterVoyage 4 Largeunstated+5%—$0.12Max input: 41K tokens → 32K tokens+1
OpenNemotron 3 Embed 8B BF16+5%——Max input: 41K tokens → 33K tokens+1HBetterDinghy Law 8B v1Open+5%——Max input: 41K tokens → 8K tokens+1mBetterMost Embed DeOpen+4%——OOpenOcten Embedding 8Bsame——Memory (4-bit): 2.4 GB → 4.5 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
VVoyage 4 Largeunstated+5%—$0.12Max input: 41K tokens → 32K tokens+1Nemotron 3 Embed 8B BF16Open+5%——Max input: 41K tokens → 33K tokens+1HDinghy Law 8B v1Open+5%——Max input: 41K tokens → 8K tokens+1mMost Embed DeOpen+4%——ModelScoreCostPriceWhat changes
Nemotron 3 Embed 8B BF16Open+5%——Max input: 41K tokens → 33K tokens+1HDinghy Law 8B v1Open+5%——Max input: 41K tokens → 8K tokens+1mMost Embed DeOpen+4%——OOcten Embedding 8BOpensame——Memory (4-bit): 2.4 GB → 4.5 GBlOcten Law 8B v1Opensame——Memory (4-bit): 2.4 GB → 4.5 GBModelScoreCostPriceWhat changes
OOcten Embedding 8BOpensame——Memory (4-bit): 2.4 GB → 4.5 GBOOcten Embedding 8B INT8Opensame——Memory (4-bit): 2.4 GB → 4.5 GBOOcten VL Embedding Large-3%——Max input: 41K tokens → 32K tokens+1OOcten Embedding 4B INT8Open-5%——OOcten Embedding 0.6BOpen-10%——Max input: 41K tokens → 33K tokensOOcten VL Embedding-11%——Max input: 41K tokens → 32K tokens+1All Octen models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 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 & RetrievalMTEB Dutch v1 · STS · Dutch84.8#10
FAQ
How much does Octen Embedding 4B cost?›
There is no per-unit API price: self-host only.
Is Octen Embedding 4B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Octen Embedding 4B, and what is it best at?›
#3 of 212 in Embeddings.
Is Octen Embedding 4B better than Dinghy Law 4B v1?›
On RTEB German beta · Mean over tasks · German, Octen Embedding 4B scores 73.3 vs 74 — about the same.
When was Octen Embedding 4B released? Is there a newer version?›
Released 2025-12-30. It is the current version in its line.
Is Octen Embedding 4B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Octen Embedding 4B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Octen Embedding 4B?›
Octen Embedding 4B is an open-weights embeddings & retrieval model from Octen, released Dec 2025.
What are the best alternatives to Octen Embedding 4B?›
Voyage 4 Large (better), Nemotron 3 Embed 8B BF16 (open weights).