Fact-checking and judges

Prometheus 2

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.

The last open version came out in Apr 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
KAIST and LG AI Research (prometheus-eval), South Korea
First release
Oct 2023
Latest release
Apr 2024
Sizes
7B – 8x7B
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Software development, Education, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Scoring chatbot answers on your own scale
  • Comparing two answer options
  • Quality checks before launching an AI service

Where it is used

AI service developmentEducation and gradingSupport quality control

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. Prometheus-BGB 8x7B
  2. Prometheus 2 7B и 8x7B
  3. Prometheus-Vision 7B и 13B
  4. Prometheus 7B и 13B

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 Prometheus 2 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 Prometheus 2 need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 Prometheus 2 support Russian?

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

Where can I download Prometheus 2 and what does it cost?

The Prometheus 2 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.

DetailsTextMistralMistral AI · FranceCommercial use with conditions

European models focused on speed. Mixtral was one of the first open mixture-of-experts models; there are versions for images (Pixtral, Medium 3.5), Lean proofs and moderation (Shieldstral).

Details

Source: huggingface.co/prometheus-eval/prometheus-bgb-8x7b-v2.0. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.