Computer visionSearch and RAGMusic and sound

Perception Encoder (PE)

Meta's family of encoders for images and video, and with PE-AV also for audio. PE-Core searches by text more accurately than SigLIP 2 (per Meta); small versions are available.

Developer
Meta, USA
First release
Apr 2025
Latest release
Dec 2025
Sizes
size not stated on the model card
License
Commercial use allowedApache 2.0
Running
On your own serverAlso runs without a GPU
Industries
Retail and marketplaces, Media and production, Security, Manufacturing and logistics
Deploy on your server Hugging Face GitHub

What it does

  • Search photos and videos by description
  • Catalog labeling and tagging
  • Search across audio and video (PE-AV)

Where it is used

E-commerceMedia and video archivesVideo surveillance and security

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. PE-AV и PE-A-Frame (звук и видео)
  2. Малые PE-Core T и S, PE-Spatial
  3. PE-Core, PE-Lang, PE-Spatial (B, L, G)

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 Perception Encoder (PE) 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 Perception Encoder (PE) 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 Perception Encoder (PE) support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Perception Encoder (PE) and what does it cost?

The Perception Encoder (PE) 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

Computer visionSigLIP (наследник CLIP)Google · USACommercial use allowed

Models that map images and text into a shared space: you can search photos by words and classify images without training. OpenAI's CLIP (2021) is the predecessor.

DetailsComputer visionDINOv2 / DINOv3Meta · USACommercial use with conditions

Foundation models that turn an image into a numeric "fingerprint". They are used to build similar-image search, classification and segmentation without large labeled datasets.

DetailsComputer visionMetaCLIP / MetaCLIP 2Meta · USANon-commercial only

Meta's open reproduction of CLIP with a transparent data collection recipe. MetaCLIP 2 is trained on multilingual data from around the world. Non-commercial license only.

Details

Source: github.com/facebookresearch/perception_models. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.