---
title: laion/CLIP-ViT-B-32-laion2B-s34B-b79K
description: 1. Model Details 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model. CLIP, 151M parameters.
canonical_url: https://superlinked.com/models/laion-clip-vit-b-32-laion2b-s34b-b79k
last_updated: 2026-05-24
---

# laion/CLIP-ViT-B-32-laion2B-s34B-b79K

1. Model Details 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model

Source: [laion/CLIP-ViT-B-32-laion2B-s34B-b79K on HuggingFace](https://huggingface.co/laion/CLIP-ViT-B-32-laion2B-s34B-b79K)

## Overview

| Field | Value |
|-------|-------|
| Architecture | CLIP |
| Parameters | 151M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 512 |
| Max sequence length | 77 tokens |
| License | mit |
| Inputs | text, image |

## Benchmarks

### Flickr30kI2TRetrieval

Domain: general · Task: retrieval · Language: en

Image-to-text retrieval: retrieve captions from images

Corpus: 31,783 · Queries: 1,000

**Quality:** ndcg at 10: 0.7744 · map at 10: 0.6783 · mrr at 10: 0.8925

**Performance (L4 b1 c16):** Corpus 1.0K tok/s · Corpus p50 219.4ms · Query 10.1 mpix/s · Query p50 235.4ms

[Reference](https://shannon.cs.illinois.edu/DenotationGraph/)