RTEB #1 domain-tuned 8B retrieval embedder from Octen AI, a LoRA fine-tune of Qwen3-Embedding-8B.
A solid 7.6B-parameter dense embedding model from Octen AI. Treat the modality benchmarks above as the leading indicator of fit — composite scoring across modalities is still maturing.
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
Access model weights, configuration files, and documentation.
See which devices can run this model and at what quality level.
Octen-Embedding-8B is a LoRA fine-tune of Qwen3-Embedding-8B by Octen AI, optimized for vertical-domain retrieval (legal, finance, healthcare, code) and long-context inputs. It supports 100+ languages with 4096-dim embeddings; it ranked #1 open-source on the RTEB retrieval benchmark in January 2026 with a mean score of 0.8045.
View on Hugging Face