clip-vit-base-patch32

Name: clip-vit-base-patch32
Author: openai

by openai

The most-downloaded CLIP variant: fast zero-shot image and text embeddings

20.3Mdl/month

994likes

HuggingFace Run it on your own data, free

Identifier

Model ID

openai/clip-vit-base-patch32

Overview

CLIP ViT-B/32 is the small, fast member of the original CLIP family, and by download volume it is the most widely used vision model on Hugging Face. It maps images and text into one shared embedding space, so a text query can retrieve images with no labelled training data.

The patch32 in the name is why it is fast: it divides a 224x224 image into 32x32 pixel patches, giving 49 patches per image instead of the 256 that ViT-L/14 produces. Fewer patches means much less compute per image, at some cost in fine detail. For large media libraries where you embed millions of frames, that is usually the right trade, which is why this variant dominates production retrieval workloads.

On Mixpeek it backs image and video-frame embedding, turning frames into vectors you query with natural language through one API.

Architecture

Vision Transformer (ViT-B/32): 12 layers, 768-dim hidden size, 32x32 pixel patches, 49 patches per 224x224 image. The text encoder is a 12-layer transformer. Both project into a shared 512-dim embedding space trained with a contrastive objective over 400M image-text pairs.

Key Capabilities

•Zero-shot image classification with no fine-tuning
•Text-to-image and image-to-image retrieval in one shared space
•512-dimensional embeddings, cheaper to store than ViT-L/14 768-dim vectors
•Roughly 5x fewer image patches than ViT-L/14, so much faster per frame
•Broad runtime support: PyTorch, TensorFlow, JAX and ONNX implementations

Use Cases on Mixpeek

•High-volume video frame embedding where per-frame cost decides the budget
•First-stage recall over large image catalogs, with a stronger model reranking the top results
•Text-to-image search across media archives and product catalogs
•CPU-bound or on-device inference where ViT-L/14 is too slow

Use clip-vit-base-patch32 on Mixpeek

Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.

Open Studio

How It Runs on Mixpeek

On Mixpeek, clip-vit-base-patch32 runs as a managed extractor inside a processing pipeline. Point a bucket of zero shot image classification data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.

Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.