Model reference · open weights
modernbert-embed-unsupervised is an open-weight embedding model from nomic-ai. modernbert-embed-base-unsupervised (FP32) weighs 298 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the nomic-ai/modernbert-embed-base-unsupervised model card, 2026-10-01
What it is
| Released by | nomic-ai |
|---|---|
| Released | 2024-12-22 |
| Parameters | 149M |
| VRAM | 298 MB for the weights |
What it runs on
| Card | Runs | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
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.
The modernbert-unsupervised model performs similarly to the nomic-embed-text-v1_unsup model
| Model | Average (56) | Classification (12) | Clustering (11) | Pair Classification (3) | Reranking (4) | Retrieval (15) | STS (10) | Overall |
|---|---|---|---|---|---|---|---|---|
| nomic-embed-text-v1_unsup | 59.9 | 71.2 | 42.5 | 83.7 | 55.0 | 48.0 | 80.8 | 30.7 |
| modernbert-embed-unsupervised | 60.03 | 72.11 | 44.34 | 82.78 | 55.0 | 47.05 | 80.33 | 31.2 |
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Benchmarks
As published on the model card: the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Classification | MTEB AmazonCounterfactualClassification (en) | accuracy | 76.209 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 39.251 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 70.152 |
| Classification | MTEB AmazonPolarityClassification | accuracy | 91.661 |
| Classification | MTEB AmazonPolarityClassification | ap | 88.673 |
| Classification | MTEB AmazonPolarityClassification | f1 | 91.653 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 46.768 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 46.153 |
| Retrieval | MTEB ArguAna | map_at_1 | 24.964 |
| Retrieval | MTEB ArguAna | map_at_10 | 39.891 |
| Retrieval | MTEB ArguAna | map_at_100 | 41.015 |
| Retrieval | MTEB ArguAna | map_at_1000 | 41.027 |
| Retrieval | MTEB ArguAna | map_at_20 | 40.789 |
| Retrieval | MTEB ArguAna | map_at_3 | 35.017 |
| Retrieval | MTEB ArguAna | map_at_5 | 37.445 |
| Retrieval | MTEB ArguAna | mrr_at_1 | 25.462 |
| Retrieval | MTEB ArguAna | mrr_at_10 | 40.081 |
| Retrieval | MTEB ArguAna | mrr_at_100 | 41.204 |
| Retrieval | MTEB ArguAna | mrr_at_1000 | 41.216 |
| Retrieval | MTEB ArguAna | mrr_at_20 | 40.979 |
| Retrieval | MTEB ArguAna | mrr_at_3 | 35.171 |
| Retrieval | MTEB ArguAna | mrr_at_5 | 37.660 |
| Retrieval | MTEB ArguAna | ndcg_at_1 | 24.964 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 48.816 |