[Models](/models)/nlpai-lab/RenderRank-2B

Apache-2.0

# RenderRank-2B

by nlpai-lab

A 2B reranker that reads documents as rendered images, matching larger text rerankers with about half the input tokens on long documents

16likes

2Bparams

[HuggingFace](https://huggingface.co/nlpai-lab/RenderRank-2B)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`nlpai-lab/RenderRank-2B`

## Deploy RenderRank-2B

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

RenderRank-2B is a document reranker from nlpai-lab, fine-tuned from Qwen3-VL-Reranker-2B and released under Apache-2.0 in September 2026. It renders a document's text as page images and scores those against a text query, which takes fewer tokens than the text itself, so more of a long document fits in the same context.

On the card's BEIR reranking test it averages 55.96 NDCG@10 using 290 input tokens per pair, ahead of Qwen3-Reranker-0.6B (54.56 at 439 tokens). On four long-document sets it averages 88.27, level with a 4B reranker while reading about half the tokens.

## Architecture

Qwen3-VL-Reranker-2B fine-tuned on rendered text. Documents are drawn as black-on-white pages (Roboto 12 pt at 96 DPI, 896 px wide, up to 56 lines), passed as visual tokens with a text query, and scored as a yes/no relevance probability. It also accepts plain text or existing page images.

## Mixpeek SDK Integration

IngestRetrieve

\# A reranker scores candidates; index and retrieve the documents with Mixpeek first.
import requests

docs = requests.post(
    "https://api.mixpeek.com/v1/retrievers/ret\_your\_retriever/execute",
    headers={"Authorization": "Bearer API\_KEY", "X-Namespace": "ns\_your\_namespace"},
    json={"inputs": {"query": "termination notice period"}},
).json()\["documents"\]

## Capabilities

*   Scores a document as plain text, as rendered page images, or from your own page images
*   Multi-page documents scored as one document
*   32,768-token context including query, template and visual tokens
*   Yes/no relevance scoring, Apache-2.0

## Use Cases on Mixpeek

Reranking long documents (reports, filings, transcripts) inside a fixed context budget

Reranking scanned or rendered PDF pages directly as images

Cutting reranker input cost on text-heavy retrieval

## Benchmarks

Dataset

Metric

Score

Source

BEIR, 11 sets (top 100 BM25 reranked)

NDCG@10 avg

55.96

Model card: nlpai-lab/RenderRank-2B (self-reported, 290 input tokens per pair; Qwen3-Reranker-0.6B 54.56 at 439; Qwen3-Reranker-4B 57.99)

Long documents (MLDR, 2WikiMQA, QMSum, SummScreenFD)

NDCG@10 avg

88.27

Model card (self-reported; Qwen3-Reranker-4B 88.15 using about twice the input tokens)

MLDR (English)

NDCG@10

99.74

Model card (4,198 input tokens per pair against 8,863 for Qwen3-Reranker-0.6B)

## Performance

Input SizeText queries; documents as text, rendered pages (896 px wide, up to 56 lines a page) or images; 32,768-token context

Embedding Dimn/a (outputs a relevance score)

GPU LatencyInput dependent

GPU ThroughputBatch dependent

GPU MemoryModel dependent

The saving is in input length: rendered documents use roughly a third fewer tokens on BEIR and about half on long documents than the text rerankers in the card's tables. Evaluated in English only. We have not measured it.

## Common Pipeline Companions

[

Qwen/Qwen3-VL-Reranker-2B

The base reranker RenderRank is fine-tuned from

](/model/Qwen/Qwen3-VL-Reranker-2B)

## Frequently Asked Questions

### How does RenderRank reduce reranking cost?

It renders document text as page images, which the vision encoder represents with fewer tokens than the original text. On the card's long-document sets it reads about half the tokens of comparable text rerankers at the same accuracy.

### Can RenderRank rerank scanned PDFs?

Yes. It takes existing page images directly, one or several pages per document, as well as plain text and text it renders itself.

### Is RenderRank free to use commercially?

Yes. It is released under Apache-2.0.

### How do I use RenderRank with Mixpeek?

Run a Mixpeek retriever for candidates, then score their text or page images with RenderRank and keep its order, as in the example on this page.

## Explore on Mixpeek

[

Browse all models

Search the full model catalog

](/models)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

Organizationnlpai-lab

Retriever\-

Parameters2B

LicenseApache-2.0

Downloads/moN/A

Likes16

[

### Research Paper

RenderRank: Learning to Rerank Text with Compressed Visual Tokens

arxiv.org](https://arxiv.org/abs/2609.35069)

### Build a pipeline with RenderRank-2B

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)