Fact-checking and judges

Nemotron Reward / GenRM

Large NVIDIA scorers for selecting and fine-tuning answers. The multilingual GenRM version lists Russian among its languages. The scorer itself makes mistakes and does not replace manual review on important tasks.

Developer
NVIDIA, USA
First release
Jun 2024
Latest release
May 2025
Sizes
49B, 70B and 340B
License
Commercial use with conditionsNVIDIA and Llama proprietary licenses — see the model card for terms
Russian
Supported
Running
On your own serverNeeds a GPU
Industries
Software development, Science and research, Customer support, Education
Deploy on your server Hugging Face

What it does

  • Choosing the best of several candidate answers
  • Preparing data to fine-tune your own model
  • Scoring assistant answers in Russian and other languages

Where it is used

IT and software developmentResearch and scienceCustomer support

Hardware requirements

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

Versions

  1. Llama-3.3-Nemotron-Super-49B-GenRM-Multilingual
  2. Llama-3.1-Nemotron-70B-Reward
  3. Nemotron-4-340B-Reward

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 Nemotron Reward / GenRM be used in a commercial project?

With conditions. License: NVIDIA and Llama proprietary licenses — see the model card for terms. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Nemotron Reward / GenRM need?

At minimum: Server with several GPUs — flagship versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Nemotron Reward / GenRM support Russian?

Yes, Russian is listed on the model card.

Where can I download Nemotron Reward / GenRM and what does it cost?

The Nemotron Reward / GenRM 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

Fact-checking and judgesSkywork-RewardSkywork (Kunlun Tech) · ChinaCommercial use with conditions

Reward models: they score how good a language model's answer is for the user. Used for fine-tuning your own models and picking the best of several answers.

DetailsFact-checking and judgesArmoRM (RLHFlow)RLHFlow · USACommercial use with conditions

An answer scorer that returns a breakdown across several attributes rather than a single overall score. The scorer itself makes mistakes and does not replace manual review on important tasks.

DetailsFact-checking and judgesPrometheus 2KAIST and LG AI Research (prometheus-eval) · South KoreaCommercial use allowed

An open judge model: it scores other models' answers against your criteria and explains the score. A replacement for paid models in the reviewer role.

Details

Source: huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.