Search and RAG

NVIDIA Nemotron Embed

NVIDIA embeddings for search and RAG. Nemotron-3-Embed, released in 2026, is under the permissive OpenMDW license and works in many languages.

Developer
NVIDIA, USA
First release
Oct 2025
Latest release
Jul 2026
Sizes
1B – 8B
License
Commercial use with conditionsNemotron-3-Embed: OpenMDW 1.1; llama-nemotron-embed-1b-v2: NVIDIA Open Model License; llama-embed-nemotron-8b: non-commercial only
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Software development, Customer support, Documents and accounting
Deploy on your server Hugging Face

What it does

  • Search across corporate documents
  • RAG for chatbots and assistants
  • Search across images and pages (VL versions)

Where it is used

Large companiesCustomer supportDocument management

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. Nemotron-3-Embed
  2. llama-nemotron-embed-vl-1b-v2
  3. llama-nemotron-embed-1b-v2
  4. llama-embed-nemotron-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.

Frequently asked questions

Can NVIDIA Nemotron Embed be used in a commercial project?

With conditions. License: Nemotron-3-Embed: OpenMDW 1.1; llama-nemotron-embed-1b-v2: NVIDIA Open Model License; llama-embed-nemotron-8b: non-commercial only. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does NVIDIA Nemotron Embed 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 NVIDIA Nemotron Embed support Russian?

Yes, Russian is listed on the model card.

Where can I download NVIDIA Nemotron Embed and what does it cost?

The NVIDIA Nemotron Embed 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.

Details

Source: huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.