Search and RAG

Granite Embedding

Lightweight IBM embeddings for enterprise search, trained on data with clear rights. R2, released in 2026, became multilingual.

Developer
IBM, USA
First release
Dec 2024
Latest release
Apr 2026
Sizes
30M – 311M
License
Commercial use allowedApache 2.0
Russian
Supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Software development, Documents and accounting, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Search across corporate documents
  • RAG on a regular server without a GPU
  • Reranking results

Where it is used

Large companiesFinance and insuranceKnowledge bases

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
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. R2 многоязычная
  2. R2 реранкер
  3. Granite Embedding R2 (английский)
  4. Granite Embedding

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 Granite 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 Granite 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 Granite Embedding support Russian?

Yes, Russian is listed on the model card.

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

The Granite 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

TextIBM GraniteIBM · USACommercial use allowed

IBM enterprise models with transparent training data and ISO 42001 certification. Granite 4 is a memory-efficient Mamba and Transformer hybrid.

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 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.

Details

Source: huggingface.co/ibm-granite/granite-embedding-311m-multilingual-r2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.