---
title: vidore/colqwen2.5-v0.2
description: ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index doc. Qwen2, 7.0B parameters.
canonical_url: https://superlinked.com/models/vidore-colqwen2-5-v0-2
last_updated: 2026-05-25
---

# vidore/colqwen2.5-v0.2

ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.

Source: [vidore/colqwen2.5-v0.2 on HuggingFace](https://huggingface.co/vidore/colqwen2.5-v0.2)
Base model: [vidore/colqwen2.5-base](https://huggingface.co/vidore/colqwen2.5-base)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Qwen2 |
| Parameters | 7.0B |
| Tasks | Encode |
| Outputs | Multi-Vec |
| Dimensions | Multi-Vec: 128 |
| Max sequence length | 2,048 tokens |
| License | mit |
| Inputs | text, image |
| Languages | en |

## Benchmarks

### Vidore3ComputerScienceRetrieval

Domain: technology · Task: retrieval · Language: en

Visual document retrieval on computer science papers and slides

**Performance (L4 b1 c16):** Corpus 7.6 mpix/s · Corpus p50 1.9s · Query 337 tok/s · Query p50 414.9ms

[Reference](https://arxiv.org/abs/2601.08620)

### Vidore3FinanceEnRetrieval

Domain: finance · Task: retrieval · Language: en

Visual document retrieval on financial reports

**Performance (L4 b1 c16):** Corpus 7.6 mpix/s · Corpus p50 1.9s · Query 315 tok/s · Query p50 413.7ms

[Reference](https://arxiv.org/abs/2601.08620)

### Vidore3HrRetrieval

Domain: general · Task: retrieval · Language: en

Visual document retrieval on HR-related documents

**Performance (L4 b1 c16):** Corpus 7.8 mpix/s · Corpus p50 1.9s · Query 377 tok/s · Query p50 429.2ms

[Reference](https://arxiv.org/abs/2601.08620)

### Vidore3PharmaceuticalsRetrieval

Domain: medical · Task: retrieval · Language: en

Visual document retrieval on pharmaceutical documents

**Performance (L4 b1 c16):** Corpus 5.4 mpix/s · Corpus p50 1.8s · Query 348 tok/s · Query p50 425.4ms

[Reference](https://arxiv.org/abs/2601.08620)