Search and RAG

Octen Embedding

Qwen3-Embedding models fine-tuned by the startup Octen for search in legal, financial and medical texts. As of January 2026 the 8B version topped the RTEB leaderboard.

Developer
Octen, USA / Singapore
First release
Dec 2025
Latest release
Apr 2026
Sizes
0.6B – 8B
License
Commercial use allowedApache 2.0
Russian
Not stated
Ready-made builds
GGUF, MLX (Apple)
Running
On your own serverAlso runs without a GPU
Industries
Legal, Finance, Healthcare, Software development
Deploy on your server Hugging Face

What it does

  • Search across contracts and case law
  • Search across financial reports
  • Search across long documents up to 32K tokens

Where it is used

Law firmsBanking and financeClinics (reference databases)

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Octen-Embedding-4B-INT8
  2. Octen-Embedding-0.6B и 8B-INT8
  3. Octen-Embedding-4B
  4. Octen-Embedding-8B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Octen Embedding be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Octen Embedding need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Octen Embedding support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download Octen Embedding and what does it cost?

The Octen Embedding weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Search and RAGQwen3 Embedding / RerankerAlibaba (Qwen) · ChinaCommercial use allowed

Embeddings and rerankers based on Qwen3, among the best open ones for multilingual search, including Russian. VL versions search images, screenshots and video.

DetailsSearch and RAGBGE-M3BAAI · ChinaCommercial use allowed

A model for meaning-based search in about a hundred languages. The core of RAG: the bot finds the right part of a document before answering.

DetailsSearch and RAGHarrier (harrier-oss)Microsoft · USACommercial use allowed

Microsoft's 2026 multilingual embeddings with context up to 32K tokens; Russian is on the language list. The 270M and 0.6B versions run on a regular server, 27B is the most accurate.

Details

Source: huggingface.co/Octen/Octen-Embedding-4B-INT8. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.