MetaCLIP / MetaCLIP 2
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.
- Developer
- Meta, USA
- First release
- Oct 2023
- Latest release
- Nov 2025
- Sizes
- 0.15B – 3.6B
- License
- Non-commercial onlyCC-BY-NC 4.0
- Running
- On your own serverAlso runs without a GPU
- Industries
- Retail and marketplaces, Media and production, Science and research
What it does
- Image search by text
- Image classification without training
- Search research and prototypes
Where it is used
Hardware requirements
Versions
- MetaCLIP 2 B/16 и L/14
- MetaCLIP 2 giant
- MetaCLIP 2 worldwide (H/14)
- MetaCLIP (B/32 – H/14)
How to run it
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 MetaCLIP / MetaCLIP 2 be used in a commercial project?
No. License: CC-BY-NC 4.0. A commercial product needs a different model or a separate agreement with the rights holder.
What hardware does MetaCLIP / MetaCLIP 2 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 MetaCLIP / MetaCLIP 2 support Russian?
Language does not matter for this model: it does not work with text.
Where can I download MetaCLIP / MetaCLIP 2 and what does it cost?
The MetaCLIP / MetaCLIP 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
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
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 visionPerception Encoder (PE)Meta · USACommercial use allowedMeta'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.
DetailsComputer visionCLIP (OpenAI)OpenAI · USACommercial use allowedThe 2021 model that first linked images and text: search photos by words and classify them without training. English only; SigLIP 2 or PE are usually chosen today.
DetailsSource: huggingface.co/facebook/metaclip-2-worldwide-b16. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


