RTEB #1 domain-tuned 8B retrieval embedder from Octen AI, a LoRA fine-tune of Qwen3-Embedding-8B.
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