Model reference · open weights

modernbert-embed-unsupervised

Available as managed deployment Embeddings nomic-ai Embeddings 1 variants 121 dl/mo

modernbert-embed-unsupervised is an open-weight embedding model from nomic-ai. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Makernomic-ai
TypeEmbedding models
TaskEmbeddings
Parameters (lead)149M
Context8k tokens
Runs withsentence-transformers
Based onanswerdotai/ModernBERT-base
Released2024-12-22
Popularity121 downloads / month
LicenceOpen weights

About

What modernbert-embed-unsupervised is

modernbert-embed-unsupervised is the unsupervised checkpoint trained with the contrastors library for 1 epoch over the 235M weakly-supervised contrastive pairs curated in Nomic Embed.

We suggest using moderbert-embed for embedding tasks.

Performance

The modernbert-unsupervised model performs similarly to the nomic-embed-text-v1_unsup model

ModelAverage (56)Classification (12)Clustering (11)Pair Classification (3)Reranking (4)Retrieval (15)STS (10)Overall
nomic-embed-text-v1_unsup59.971.242.583.755.048.080.830.7
modernbert-embed-unsupervised60.0372.1144.3482.7855.047.0580.3331.2

From the published model card. Full card on the HuggingFace links in the sidebar.

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
ClassificationMTEB AmazonCounterfactualClassification (en)accuracy76.209
ClassificationMTEB AmazonCounterfactualClassification (en)ap39.251
ClassificationMTEB AmazonCounterfactualClassification (en)f170.152
ClassificationMTEB AmazonPolarityClassificationaccuracy91.661
ClassificationMTEB AmazonPolarityClassificationap88.673
ClassificationMTEB AmazonPolarityClassificationf191.653
ClassificationMTEB AmazonReviewsClassification (en)accuracy46.768
ClassificationMTEB AmazonReviewsClassification (en)f146.153
RetrievalMTEB ArguAnamap_at_124.964
RetrievalMTEB ArguAnamap_at_1039.891
RetrievalMTEB ArguAnamap_at_10041.015
RetrievalMTEB ArguAnamap_at_100041.027
RetrievalMTEB ArguAnamap_at_2040.789
RetrievalMTEB ArguAnamap_at_335.017
RetrievalMTEB ArguAnamap_at_537.445
RetrievalMTEB ArguAnamrr_at_125.462
RetrievalMTEB ArguAnamrr_at_1040.081
RetrievalMTEB ArguAnamrr_at_10041.204
RetrievalMTEB ArguAnamrr_at_100041.216
RetrievalMTEB ArguAnamrr_at_2040.979
RetrievalMTEB ArguAnamrr_at_335.171
RetrievalMTEB ArguAnamrr_at_537.660
RetrievalMTEB ArguAnandcg_at_124.964
RetrievalMTEB ArguAnandcg_at_1048.816

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys modernbert-embed-unsupervised for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (modernbert-embed-unsupervised below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"modernbert-embed-unsupervised","input":"text to embed"}'

Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.

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