Octen Embedding 4B INT8 measured on 5 of 261 Embeddings benchmarks5
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
64.2RTEB French beta
Apr 2026released
2,560Dimensions
41K tokensMax input
en, zhLanguages
Alternatives?
ModelScoreCostPriceWhat changes
VBetterVoyage 4 Largeunstated+8%—$0.12Max input: 41K tokens → 32K tokens+1
OpenNemotron 3 Embed 8B BF16same——Max input: 41K tokens → 33K tokens+1OOpenOcten Embedding 4Bsame——OpenNV Embed v2unstated-4%——Max input: 41K tokens → 33K tokens+2OOpenOcten Embedding 8B-4%——Memory (4-bit): 2.4 GB → 4.5 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
VVoyage 4 Largeunstated+8%—$0.12Max input: 41K tokens → 32K tokens+1ModelScoreCostPriceWhat changes
Nemotron 3 Embed 8B BF16Opensame——Max input: 41K tokens → 33K tokens+1OOcten Embedding 4BOpensame——NV Embed v2unstatedOpen-4%——Max input: 41K tokens → 33K tokens+2OOcten Embedding 8BOpen-4%——Memory (4-bit): 2.4 GB → 4.5 GBOOcten Embedding 8B INT8Open-6%——Memory (4-bit): 2.4 GB → 4.5 GBModelScoreCostPriceWhat changes
OOcten Embedding 4BOpensame——OOcten Embedding 8BOpen-4%——Memory (4-bit): 2.4 GB → 4.5 GBOOcten Embedding 8B INT8Open-6%——Memory (4-bit): 2.4 GB → 4.5 GBOOcten VL Embedding Large-7%——Max input: 41K tokens → 32K tokens+1OOcten VL Embedding-20%——Max input: 41K tokens → 32K tokens+1OOcten Embedding 0.6BOpen-28%——Max input: 41K tokens → 33K tokensAll 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 & RetrievalFAQ
How much does Octen Embedding 4B INT8 cost?›
There is no per-unit API price: self-host only.
Is Octen Embedding 4B INT8 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Octen Embedding 4B INT8, and what is it best at?›
#4 of 212 in Embeddings.
Is Octen Embedding 4B INT8 better than Octen Embedding 4B?›
On RTEB French beta · Mean over tasks · multilingual (2 languages), Octen Embedding 4B INT8 scores 64.2 vs 64.6 — about the same.
When was Octen Embedding 4B INT8 released? Is there a newer version?›
Released 2026-04-02. It is the current version in its line.
Is Octen Embedding 4B INT8 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Octen Embedding 4B INT8 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Octen Embedding 4B INT8?›
Octen Embedding 4B INT8 is an open-weights embeddings & retrieval model from Octen, released Apr 2026.
What are the best alternatives to Octen Embedding 4B INT8?›
Voyage 4 Large (better), Nemotron 3 Embed 8B BF16 (open weights).