TextImage + textVoice assistants

NVIDIA Nemotron

NVIDIA models for agents and reasoning, optimized to run fast on its GPUs. Nemotron 3 is a Mamba and MoE hybrid from 4B to 550B; Nano Omni handles video, audio and images (English only).

Developer
NVIDIA, USA
First release
Jun 2024
Latest release
Aug 2026
Sizes
4B – 550B-A55B
License
Commercial use with conditionsNemotron-4, Llama-Nemotron, Nemotron 3 Nano, Nano Omni, Cascade 2 and Super: NVIDIA Open Model License / Open Model Agreement (commercial use allowed with conditions; Llama-based versions add Llama terms); Nemotron 3 Ultra and 3.5 Lightning: OpenMDW-1.1
Russian
Not supported
Ready-made builds
GGUF, AWQ, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Software development, Manufacturing and logistics, Science and research
Deploy on your server Hugging Face

What it does

  • Agents with tool calling
  • Reasoning and calculation tasks
  • Answers based on long documents
  • Synthetic training data generation

Where it is used

IT and developmentIndustryLarge companies with their own GPU cluster

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
fits

Versions

  1. Nemotron 3.5 Lightning 30B-A3B
  2. Nemotron 3 Ultra 550B-A55B
  3. Nemotron 3 Nano Omni 30B-A3B
  4. Nemotron 3 Super 120B-A12B / Nano 4B / Cascade 2 30B-A3B
  5. Nemotron 3 Nano 30B-A3B
  6. Nemotron Nano 2 (9B, 12B)
  7. Llama-Nemotron Ultra 253B
  8. Llama-3.1-Nemotron-70B
  9. Nemotron-4 340B

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 NVIDIA Nemotron be used in a commercial project?

With conditions. License: Nemotron-4, Llama-Nemotron, Nemotron 3 Nano, Nano Omni, Cascade 2 and Super: NVIDIA Open Model License / Open Model Agreement (commercial use allowed with conditions; Llama-based versions add Llama terms); Nemotron 3 Ultra and 3.5 Lightning: OpenMDW-1.1. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does NVIDIA Nemotron 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 support Russian?

No. The model card lists its languages and Russian is not among them.

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

The NVIDIA Nemotron 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.

Comparisons

Similar models

TextLlamaMeta · USACommercial use with conditions

The models that started mass open source in AI. A huge ecosystem of fine-tuned versions and tools.

DetailsTextQwenAlibaba · ChinaCommercial use with conditions

A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.

DetailsTextIBM 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.

Details

Source: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.