Search and RAG

FRIDA / Giga-Embeddings

Sber embeddings built for Russian: according to the developers, among the best on Russian-language search benchmarks. FRIDA is compact, Giga-Embeddings is more powerful.

Developer
Sber (SberDevices), Russia
First release
Dec 2024
Latest release
Aug 2026
Sizes
480M – 10B-A1.8B
License
Commercial use allowedMIT
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Software development, Customer support, Documents and accounting, Public sector
Deploy on your server Hugging Face

What it does

  • Search across Russian-language documents
  • RAG for chatbots in Russian
  • Classifying requests and reviews

Where it is used

Banking and financePublic sector and legalCustomer support

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. Giga-Embeddings-instruct 0826 (480M, 10B-A1.8B)
  2. Giga-Embeddings-instruct 0826 (3B)
  3. Giga-Embeddings-instruct
  4. FRIDA

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.

Frequently asked questions

Can FRIDA / Giga-Embeddings be used in a commercial project?

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

What hardware does FRIDA / Giga-Embeddings 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 FRIDA / Giga-Embeddings support Russian?

Yes, Russian is listed on the model card.

Where can I download FRIDA / Giga-Embeddings and what does it cost?

The FRIDA / Giga-Embeddings 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 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 RAGE5 / multilingual-e5Microsoft · USACommercial use allowed

Proven models for semantic search. The multilingual versions work well with Russian and are still a reliable base for RAG.

DetailsSearch 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.

Details

Source: huggingface.co/ai-sage/Giga-Embeddings-instruct-480M-0826. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.