Octen Embedding 0.6B measured on 18 of 261 Embeddings benchmarks18
BenchmarkByScoreRank
Reranking6
Other12
No benchmark matches
price not verifiedprice
46.1RTEB French beta
Jan 2026released
1,024Dimensions
33K tokensMax input
en, zhLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+4%—$0.002Max input: 33K tokens → 2K tokens+1GOpenSTS Multilingual Mpnet Base v2unstated+19%——Max input: 33K tokens → 0K tokens+1
BetterQwen 3 Embedding 8BunstatedOpen+13%—$0.01Languages: not verified+1iBetterMultilingual E5 Large InstructunstatedOpen+7%—$0.01Max input: 33K tokens → 1K tokensiBetterMultilingual E5 LargeunstatedOpen+4%—$0.01Max input: 33K tokens → 1K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+4%—$0.002Max input: 33K tokens → 2K tokens+1Qwen 3 Embedding 8BunstatedOpen+13%—$0.01Languages: not verified+1iMultilingual E5 Large InstructunstatedOpen+7%—$0.01Max input: 33K tokens → 1K tokensiMultilingual E5 LargeunstatedOpen+4%—$0.01Max input: 33K tokens → 1K tokens
Jina Embeddings v5 Text NanounstatedOpen+12%—$0.02Max input: 33K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
GSTS Multilingual Mpnet Base v2unstatedOpen+19%——Max input: 33K tokens → 0K tokens+1Qwen 3 Embedding 8BunstatedOpen+13%—$0.01Languages: not verified+1OOcten Embedding 8BOpen+13%——Memory (4-bit): 0.4 GB → 4.5 GBJina Embeddings v5 Text NanounstatedOpen+12%—$0.02Max input: 33K tokens → 8K tokens+1
Llama Embed Nemotron 8BOpen+12%——Languages: not verified+1ModelScoreCostPriceWhat changes
OOcten Embedding 8BOpen+13%——Memory (4-bit): 0.4 GB → 4.5 GBOOcten Embedding 4BOpen+10%——Memory (4-bit): 0.4 GB → 2.4 GBOOcten VL Embeddingn/a——Max input: 33K tokens → 32K tokens+1OOcten VL Embedding Largen/a——Max input: 33K tokens → 32K tokens+1OOcten Embedding 4B INT8Openn/a——Memory (4-bit): 0.4 GB → 2.4 GBOOcten Embedding 8B INT8Openn/a——Memory (4-bit): 0.4 GB → 4.5 GBAll Octen 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 & RetrievalMTEB Dutch v1 · STS · Dutch77.1#45
FAQ
How much does Octen Embedding 0.6B cost?›
There is no per-unit API price: price not verified.
How good is Octen Embedding 0.6B, and what is it best at?›
#47 of 212 in Embeddings.
Is Octen Embedding 0.6B better than E5 Base Trm Nl?›
On MTEB Dutch v1 · STS · Dutch, Octen Embedding 0.6B scores 77.1 vs 77.2 — about the same.
When was Octen Embedding 0.6B released? Is there a newer version?›
Released 2026-01-10. It is the current version in its line.
Is Octen Embedding 0.6B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Octen Embedding 0.6B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Octen Embedding 0.6B?›
Octen Embedding 0.6B is an open-weights embeddings & retrieval model from Octen, released Jan 2026.
What are the best alternatives to Octen Embedding 0.6B?›
EmbeddingGemma 300M (better), STS Multilingual Mpnet Base v2 (open weights).