n

Nomic Embed Text v1 Unsupervised

Jan 2024
nNomic Embed Text v1 Unsupervised
Compare in
on
self-host onlyprice
49.4MTEB English v2
Jan 2024released
8K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Jina Embeddings v5 Text Nano78.12STS Multilingual Mpnet Base v276.63Bilingual Embedding Large75.94F2LLM v2 14B75.25Jina Embeddings v374.7
···
54Sentence Croissant Alpha v0.357.655Nomic Embed Text v1 Unsupervised57.656Cohere Embed English v3.057.3

Strong at

C
Embeddings & Retrieval#110 of 200

Alternatives?

ModelScoreCostPriceWhat changes
iBetterMultilingual E5 Large InstructunstatedOpen+28%—$0.01Max input: 8K tokens → 1K tokens+1OpenJina Embeddings v5 Text Nanounstated+36%—$0.02Languages: not verifiediBetterMultilingual E5 LargeunstatedOpen+24%—$0.01Max input: 8K tokens → 1K tokens+1iBetterE5 Mistral 7B InstructunstatedOpen+17%—$0.022Memory (4-bit): 0.1 GB → 4.3 GBBetterJina Embeddings v3unstatedOpen+30%—$0.05Memory (4-bit): 0.1 GB → 0.3 GB

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English48#119
BEIR · Mean over task types · English48#119
BEIR · Retrieval · English48#119
MTEB Persian v2 · Reranking · Persian44#67
JMTEB v2 · Clustering · Japanese21.9#84
JMTEB v2 · STS · Japanese65.1#82
LongEmbed · Mean over tasks · English55.5#40
LongEmbed · Mean over task types · English55.5#40
LongEmbed · Retrieval · English55.5#40
MTEB German v1 · Mean over tasks · German42.9#44
MTEB German v1 · Mean over task types · German41.6#45
MTEB German v1 · Clustering · German25#82
MTEB German v1 · Retrieval · German44#33
MTEB German v1 · Classification · German50.3#89
MTEB German v1 · STS · German57.6#55
MTEB German v1 · Pair Classification · German49.6#97
MTEB German v1 · Reranking · German23.2#92
MTEB Europe v1 · Retrieval · multilingual (25 languages)46#47
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)40.6#114
MTEB Europe v1 · Classification · multilingual (23 languages)50.9#75
MTEB Europe v1 · Clustering · multilingual (29 languages)35#112
MTEB Europe v1 · Instruction Reranking · English-2.1#131
MTEB Europe v1 · Pair Classification · multilingual (11 languages)83#89
MTEB Europe v1 · Reranking · multilingual (12 languages)52.5#83
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)11.5#113
MTEB French v1 · Mean over tasks · multilingual (2 languages)50.5#43
MTEB French v1 · Mean over task types · multilingual (2 languages)52.2#41
MTEB French v1 · STS · French72.3#47
MTEB French v1 · Retrieval · multilingual (2 languages)40.5#55
MTEB French v1 · Reranking · French69.4#64
MTEB French v1 · Clustering · French40.5#64
MTEB French v1 · Classification · French55.5#69
MTEB French v1 · Summarization · French29.8#93
MTEB French v1 · Pair Classification · French57.3#104
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)36.3#64
MTEB Indic v1 · Mean over task types · multilingual (25 languages)27.2#60
MTEB Indic v1 · Classification · multilingual (8 languages)46.1#68
MTEB Indic v1 · Retrieval · multilingual (14 languages)23.1#77
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)5.5#86
MTEB Indic v1 · Reranking · multilingual (2 languages)62.9#101
MTEB Indic v1 · Pair Classification · Hindi53.3#137
MTEB Indic v1 · STS · multilingual (13 languages)-4.3#190
MTEB Indic v1 · Clustering · multilingual (21 languages)3.4#141
MTEB Korean v2 · Reranking · Korean9.9#106
MTEB Korean v2 · Classification · Korean22#97
MTEB Dutch v1 · Reranking · Dutch81.8#104
MTEB Polish v1 · Pair Classification · Polish64#100
MTEB Polish v1 · Classification · Polish43.1#75
MTEB Polish v1 · STS · Polish57.9#61
MTEB Portuguese v1 · Multilabel Classification · Portuguese21#56
MTEB Law v1 · Mean over tasks · multilingual (3 languages)45.5#58
MTEB Law v1 · Mean over task types · multilingual (3 languages)45.5#58
MTEB Law v1 · Retrieval · multilingual (3 languages)45.5#58
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)40.9#57
MTEB Medical v1 · Mean over task types · multilingual (10 languages)33.8#68
MTEB Medical v1 · Retrieval · multilingual (10 languages)44.4#60
MTEB Medical v1 · Clustering · English33.7#149
MTEB Medical v1 · Reranking · Mandarin Chinese23.2#117
FollowIR · Mean over tasks · English-2.1#131
FollowIR · Mean over task types · English-2.1#131
FollowIR · Instruction Reranking · English-2.1#131
MTEB Spanish v1 · Pair Classification · Spanish57.4#133
MTEB Spanish v1 · Clustering · Spanish44.8#40
MTEB Spanish v1 · Reranking · Spanish37.3#81
MTEB Thai v1 · Clustering · Thai3.2#174
MTEB Thai v1 · Pair Classification · Thai51#172
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)33.9#87
MTEB Scandinavian v1 · Classification · multilingual (6 languages)48.4#105
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)64.9#93
MTEB Russian v1.1 · Mean over tasks · Russian30.5#65
MTEB Russian v1.1 · Mean over task types · Russian31.1#65
MTEB Russian v1.1 · Classification · Russian32.7#102
MTEB Russian v1.1 · STS · Russian49.4#79
MTEB Russian v1.1 · Reranking · Russian28.1#94
MTEB Russian v1.1 · Clustering · Russian19.2#102
MTEB Russian v1.1 · Pair Classification · Russian47.1#167
MTEB Russian v1.1 · Retrieval · Russian15.5#59
MTEB Russian v1.1 · Multilabel Classification · Russian25.6#135
RTEB French beta · Mean over tasks · multilingual (2 languages)23.4#117
RTEB German beta · Mean over tasks · German30.4#99
RTEB Law beta · Mean over tasks · multilingual (4 languages)38.3#87
MTEB multilingual v2 · Classification · multilingual (119 languages)49#93
MTEB multilingual v2 · Clustering · multilingual (208 languages)39.1#107
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)71.7#123
MTEB multilingual v2 · Retrieval · multilingual (120 languages)40.7#89
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)27.4#107
MTEB multilingual v2 · Instruction Reranking · English-2.1#131
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)16.4#106
MTEB multilingual v2 · Reranking · multilingual (22 languages)48.2#96

FAQ

How much does Nomic Embed Text v1 Unsupervised cost?›

There is no per-unit API price: self-host only.

Is Nomic Embed Text v1 Unsupervised free to use?›

There is no free API. The weights are open, so you can run it yourself.

How good is Nomic Embed Text v1 Unsupervised, and what is it best at?›

#110 of 200 in Embeddings.

Is Nomic Embed Text v1 Unsupervised better than Sentence Croissant Alpha v0.3?›

On MTEB German v1 · STS · German, Nomic Embed Text v1 Unsupervised scores 57.6 vs 57.6 — about the same.

When was Nomic Embed Text v1 Unsupervised released? Is there a newer version?›

Released 2024-01-15. It is the current version in its line.

Is Nomic Embed Text v1 Unsupervised open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Nomic Embed Text v1 Unsupervised locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is Nomic Embed Text v1 Unsupervised?›

Nomic Embed Text v1 Unsupervised is an open-weights embeddings & retrieval model from nomic-ai, released Jan 2024.

What are the best alternatives to Nomic Embed Text v1 Unsupervised?›

Multilingual E5 Large Instruct (better), Jina Embeddings v5 Text Nano (open weights).