---
title: mixedbread-ai/mxbai-edge-colbert-v0-32m (Encode)
description: The crispy, lightweight ColBERT family from Mixedbread.. ModernBERT, 32M parameters.
canonical_url: https://superlinked.com/models/mixedbread-ai-mxbai-edge-colbert-v0-32m--encode
last_updated: 2026-05-24
---

# mixedbread-ai/mxbai-edge-colbert-v0-32m (Encode)

The crispy, lightweight ColBERT family from Mixedbread.

Source: [mixedbread-ai/mxbai-edge-colbert-v0-32m on HuggingFace](https://huggingface.co/mixedbread-ai/mxbai-edge-colbert-v0-32m)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 32M |
| Tasks | Encode, Score |
| Outputs | Multi-Vec |
| Dimensions | Multi-Vec: 64 |
| Max sequence length | 8,192 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Performance (L4 b1 c16):** Corpus 28.3K tok/s · Corpus p50 60.5ms · Query 3.0K tok/s · Query p50 55.7ms

[Reference](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)

### CosQA

Domain: technology · Task: retrieval · Language: en

Code search with natural language queries

Corpus: 6,267 · Queries: 500

**Performance (L4 b1 c16):** Corpus 15.0K tok/s · Corpus p50 51.8ms · Query 1.9K tok/s · Query p50 48.5ms

[Reference](https://arxiv.org/abs/2105.13239)

### FiQA2018

Domain: finance · Task: retrieval · Language: en

Financial opinion mining and question answering

Corpus: 57,599 · Queries: 648

**Performance (L4 b1 c16):** Corpus 38.9K tok/s · Corpus p50 57.5ms · Query 3.7K tok/s · Query p50 48.0ms

[Reference](https://sites.google.com/view/fiqa/)

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Performance (L4 b1 c16):** Corpus 87.3K tok/s · Corpus p50 76.5ms · Query 5.4K tok/s · Query p50 48.3ms

[Reference](https://huggingface.co/datasets/nguha/legalbench)

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.3376 · map at 10: 0.1285 · mrr at 10: 0.5432

**Performance (L4 b1 c16):** Corpus 67.7K tok/s · Corpus p50 58.6ms · Query 1.4K tok/s · Query p50 53.0ms

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### SCIDOCS

Domain: scientific · Task: retrieval · Language: en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 · Queries: 1,000

**Performance (L4 b1 c16):** Corpus 36.4K tok/s · Corpus p50 70.2ms · Query 2.7K tok/s · Query p50 61.8ms

[Reference](https://allenai.org/data/scidocs)

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Performance (L4 b1 c16):** Corpus 58.8K tok/s · Corpus p50 61.2ms · Query 5.4K tok/s · Query p50 49.0ms

[Reference](https://github.com/allenai/scifact)

### StackOverflowQA

Domain: technology · Task: retrieval · Language: en

Programming question answering from Stack Overflow

Corpus: 19,931 · Queries: 1,994

**Performance (L4 b1 c16):** Corpus 52.8K tok/s · Corpus p50 58.9ms · Query 68.3K tok/s · Query p50 66.6ms

[Reference](https://arxiv.org/abs/2407.02883)