Model reference · open weights

deepset-mxbai-embed-de-large

Embeddings mixedbread-ai Embeddings 1 build Open weights 123k dl/mo

deepset-mxbai-embed-de-large is an open-weight embedding model from mixedbread-ai. deepset-mxbai-embed-de-large-v1 (FP16) weighs 974 MB; the smallest configuration that runs it is RTX 3060 12 GB.

  • deepset-mxbai-embed-de-large is a 487M parameter feature-extraction model developed by mixedbread-ai in collaboration with deepset.
  • It is optimized for retrieval tasks and supports German and English with a context length of 514 tokens.
  • The model is released under the Apache 2.0 license and supports binary quantization and Matryoshka Representation Learning.

Summary of the mixedbread-ai/deepset-mxbai-embed-de-large-v1 model card, 2026-10-01

What it is

Released bymixedbread-ai
Released2024-07-12
Parameters487M
VRAM974 MB for the weights

What it runs on

Memory and cards for deepset-mxbai-embed-de-large-v1 (FP16)

974 MBweights, file size
1.1 GBruntime overhead
CardRunsMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What mixedbread-ai says about deepset-mxbai-embed-de-large

Read the model card

This model is a powerful open-source German/English embedding model developed by Mixedbread in collaboration with deepset. It's built upon intfloat/multilingual-e5-large and trained using the AnglE loss. Read more details in our blog post.

In a bread loaf:

  • State-of-the-art performance
  • Supports both binary quantization and Matryoshka Representation Learning (MRL).
  • Fine-tuned on 30+ million pairs of high-quality German data
  • Optimized for retrieval tasks
  • Supported Languages: German and English.
  • Requires a prompt: query: {query} for the query and passage: {doc} for the document

Performance

On the NDCG@10 metric, our model achieves an average performance of 51.7, setting a new standard for open-source German embedding models:

ModelAvg. Performance (NDCG@10)Binary SupportMRL Support
deepset-mxbai-embed-de-large-v151.7✅✅
multilingual-e5-large50.5❌❌
jina-embeddings-v2-base-de50.0✅❌
Closed Source Models
Cohere Multilingual v352.4✅-

In a case study with a legal data client, our model outperformed domain-specific alternatives:

ModelAvg. Performance (MAP@10)
deepset-mxbai-embed-de-large-v190.25
voyage-law-284.80

Binary Quantization and Matryoshka

Our model supports both binary quantization and Matryoshka Representation Learning (MRL), allowing for significant efficiency gains:

  • Binary quantization: Retains 91.8% of performance while increasing efficiency by a factor of 32
  • MRL: A 25% reduction in vector size still leaves 97.5% of model performance
  • At 512 dimensions, over 93% of model performance remains while cutting embedding sizes in half

These optimizations can lead to substantial reductions in infrastructure costs for cloud computing and vector databases. Read more here.

Quickstart

Here are several ways to produce German sentence embeddings using our model. Note that you need to provide the prompt: query: {query} for the query and passage: {doc} for the document.

pip install -U mixedbread-ai
import { MixedbreadAIClient } from "@mixedbread-ai/sdk";

# 1. Create Client
const mxbai = new MixedbreadAIClient({
  apiKey: "YOUR_API_KEY"
});

# 2. Encode
query = 'query: Warum sollte man biologisches Brot kaufen?'

docs = [
  query,
  "passage: In unserer Bäckerei bieten wir auch glutenfreies Brot an, das für Menschen mit Zöliakie geeignet ist.",
  "passage: Kuchen und Gebäck sind ebenfalls Teil unseres Angebots, wobei wir auf höchste Qualität und Frische achten.",
  "passage: Wir haben auch eine Auswahl an herzhaften Snacks und Sandwiches, die perfekt für die Mittagspause sind."
  "passage: Biologisches Brot wird aus natürlichen Zutaten hergestellt und enthält keine künstlichen Zusatzstoffe. Es ist gesünder und umweltfreundlicher.",
  "passage: Unsere Bäckerei bietet eine Vielzahl von Brotsorten an, darunter auch biologisches Brot. Es schmeckt besser und ist frei von chemischen Konservierungsstoffen.",
  "passage: Kunden bevorzugen zunehmend biologisches Brot, da es nicht nur gut für die Gesundheit ist, sondern auch einen positiven Beitrag zur Umwelt leistet."
]

const res = await mxbai.embeddings({
  model: 'mixedbread-ai/deepset-mxbai-embed-de-large-v1',
  input: docs,
  normalized: true,
  encoding_format: 'float' # or 'binary' for binary embeddings
})

console.log(res.data[0].embedding)

API Reference

pip install -U haystack-ai mixedbread-ai-haystack
from haystack.components.embedders import SentenceTransformersTextEmbedder, SentenceTransformersDocumentEmbedder

text_embedder = SentenceTransformersTextEmbedder(model="mixedbread-ai/deepset-mxbai-embed-de-large-v1")

document_embedder = SentenceTransformersDocumentEmbedder(model="mixedbread-ai/deepset-mxbai-embed-de-large-v1")

# Or use the Mixedbread API with binary embeddings
from mixedbread_ai_haystack import  MixedbreadAITextEmbedder, MixedbreadAIDocumentEmbedder
from mixedbread_ai import EncodingFormat

text_embedder = MixedbreadAITextEmbedder( model="mixedbread-ai/deepset-mxbai-embed-de-large-v1",
                                          encoding_format=EncodingFormat.BINARY)

document_embedder = MixedbreadAIDocumentEmbedder(model="mixedbread-ai/deepset-mxbai-embed-de-large-v1",
                                                 encoding_format=EncodingFormat.BINARY)
pip install -U angle-emb
from angle_emb import AnglE
from angle_emb.utils import cosine_similarity

# 1. Specify preferred dimensions
dimensions = 1024

# 2. Load model and set pooling strategy to avg
model = AnglE.from_pretrained(
    "mixedbread-ai/deepset-mxbai-embed-de-large-v1",
    pooling_strategy='avg').cuda()

query = 'query: Warum sollte man biologisches Brot kaufen?'

docs = [
  query,
  "passage: In unserer Bäckerei bieten wir auch glutenfreies Brot an, das für Menschen mit Zöliakie geeignet ist.",
  "passage: Kuchen und Gebäck sind ebenfalls Teil unseres Angebots, wobei wir auf höchste Qualität und Frische achten.",
  "passage: Wir haben auch eine Auswahl an herzhaften Snacks und Sandwiches, die perfekt für die Mittagspause sind."
  "passage: Biologisches Brot wird aus natürlichen Zutaten hergestellt und enthält keine künstlichen Zusatzstoffe. Es ist gesünder und umweltfreundli

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms