Model reference · open weights
nomic-embed-text-unsupervised is an open-weight embedding model from nomic-ai. nomic-embed-text-v1-unsupervised (BF16) weighs 547 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the nomic-ai/nomic-embed-text-v1-unsupervised model card, 2026-10-01
What it is
| Released by | nomic-ai |
|---|---|
| Released | 2024-01-15 |
| VRAM | 547 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
nomic-embed-text-v1-unsupervised is 8192 context length text encoder. This is a checkpoint after contrastive pretraining from multi-stage contrastive training of the
final model. The purpose of releasing this checkpoint is to open-source training artifacts from our Nomic Embed Text tech report here
If you want to use a model to extract embeddings, we suggest using nomic-embed-text-v1.
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 | 76.985 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 39.472 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 70.592 |
| Classification | MTEB AmazonPolarityClassification | accuracy | 87.540 |
| Classification | MTEB AmazonPolarityClassification | ap | 83.161 |
| Classification | MTEB AmazonPolarityClassification | f1 | 87.523 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 46.808 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 46.263 |
| Retrieval | MTEB ArguAna | map_at_1 | 30.583 |
| Retrieval | MTEB ArguAna | map_at_10 | 46.170 |
| Retrieval | MTEB ArguAna | map_at_100 | 47.115 |
| Retrieval | MTEB ArguAna | map_at_1000 | 47.121 |
| Retrieval | MTEB ArguAna | map_at_3 | 41.489 |
| Retrieval | MTEB ArguAna | map_at_5 | 44.046 |
| Retrieval | MTEB ArguAna | mrr_at_1 | 30.939 |
| Retrieval | MTEB ArguAna | mrr_at_10 | 46.289 |
| Retrieval | MTEB ArguAna | mrr_at_100 | 47.241 |
| Retrieval | MTEB ArguAna | mrr_at_1000 | 47.247 |
| Retrieval | MTEB ArguAna | mrr_at_3 | 41.596 |
| Retrieval | MTEB ArguAna | mrr_at_5 | 44.149 |
| Retrieval | MTEB ArguAna | ndcg_at_1 | 30.583 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 54.812 |
| Retrieval | MTEB ArguAna | ndcg_at_100 | 58.605 |
| Retrieval | MTEB ArguAna | ndcg_at_1000 | 58.753 |