ruCLIP (ai-forever)
A Russian version of CLIP: matches images with Russian captions. Lets you search photos by description and sort images into categories without training.
The last open version came out in Jan 2022. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.
- Developer
- Sber AI and SberDevices (ai-forever), Russia
- First release
- Jan 2022
- Latest release
- Jan 2022
- Sizes
- 150M – 430M
- License
- Commercial use allowedApache 2.0 (GitHub repository)
- Russian
- Supported
- Running
- On your own serverAlso runs without a GPU
- Industries
- Retail and marketplaces, Media and production
What it does
- Product search by photo and by Russian description
- Sorting images into categories without labeling
- Checking that a photo matches its caption
Where it is used
Hardware requirements
Versions
- ruCLIP ViT-L/14 336
- ruCLIP ViT-B/32, B/16, L/14 (224 и 384 пикселя)
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 ruCLIP (ai-forever) be used in a commercial project?
Yes. License: Apache 2.0 (GitHub repository). It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does ruCLIP (ai-forever) 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 ruCLIP (ai-forever) support Russian?
Yes, Russian is listed on the model card.
Where can I download ruCLIP (ai-forever) and what does it cost?
The ruCLIP (ai-forever) 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.
DetailsSearch and RAGJina EmbeddingsJina AI · GermanyCommercial use with conditionsStrong multilingual embeddings with long context; v5-omni understands text, images and audio. Recent versions are open for non-commercial use only.
DetailsSource: huggingface.co/ai-forever/ruclip-vit-large-patch14-336. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


