nvidia/Nemotron-3-Embed-1B-BF16
Multilingual 1B embedding model for retrieval, semantic search, and RAG with flexible 2048-dim vectors.
azureFoundry/azure-huggingface/nvidia--nemotron-3-embed-1b-bf16@1
Multilingual 1B embedding model for retrieval, semantic search, and RAG with flexible 2048-dim vectors.
Specifications & capabilities
- Input
- text
- Output
- embeddings
- Context window · tokens
- 32768
- Published model ID
- Nemotron-3-Embed-1B-BF16
- Capabilities
- embeddings
Evaluations
1–9 / 9
90.44%
- source id
- mteb
- leaderboard name
- MTEB Reranking
- dimension
- embedding
- metric
- Average task score
- rank
- 8
- sample size
- 1
- aggregation scope
- task_count
- 1
- task_names
- WikipediaRerankingMultilingual
- sample_size
- 1
- subset_count
- 1
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗72.772%
- source id
- mteb
- leaderboard name
- MTEB Summarization
- dimension
- embedding
- metric
- Average task score
- rank
- 23
- sample size
- 1
- aggregation scope
- task_count
- 1
- sample_size
- 1
- subset_count
- 1
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗68.155%
- source id
- mteb
- leaderboard name
- MTEB Retrieval
- dimension
- embedding
- metric
- Average task score
- rank
- 200
- sample size
- 64
- aggregation scope
- subsets
- default
- english
- french
- german
- italian
- nl
- nld
- nld_Latn-nld_Latn
- portuguese
- spanish
- task_count
- 24
- task_names
- BelebeleRetrieval
- ChatDoctorRetrieval
- DS1000Retrieval
- DutchNewsArticlesRetrieval
- FinanceBenchRetrieval
- FreshStackRetrieval
- GermanQuAD-Retrieval
- HC3FinanceRetrieval
- HumanEvalRetrieval
- LegalQANLRetrieval
- MBPPRetrieval
- OpenTenderRetrieval
- VABBRetrieval
- Vidore3ComputerScienceRetrieval.v2
- Vidore3EnergyRetrieval.v2
- Vidore3FinanceEnRetrieval.v2
- Vidore3FinanceFrRetrieval.v2
- Vidore3HrRetrieval.v2
- Vidore3IndustrialRetrieval.v2
- Vidore3PharmaceuticalsRetrieval.v2
- Vidore3PhysicsRetrieval.v2
- WebFAQRetrieval
- WikipediaRetrievalMultilingual
- bBSARDNLRetrieval
- sample_size
- 64
- subset_count
- 10
- subset_sample
- default
- english
- french
- german
- italian
- nl
- nld
- nld_Latn-nld_Latn
- portuguese
- spanish
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗57.475%
- source id
- mteb
- leaderboard name
- MTEB Pair Classification
- dimension
- embedding
- metric
- Average task score
- rank
- 231
- sample size
- 4
- aggregation scope
- task_count
- 3
- task_names
- PawsXPairClassification
- SICKNLPairClassification
- XLWICNLPairClassification
- sample_size
- 4
- subset_count
- 2
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗59.228%
- source id
- mteb
- leaderboard name
- MTEB Other
- dimension
- embedding
- metric
- Average task score
- rank
- 260
- sample size
- 241
- aggregation scope
- splits
- all
- dentistry_and_oral_health
- dermatology
- gastroenterology
- genetics
- neuroscience_and_neurology
- orthopedic_surgery
- otorhinolaryngology
- plastic_surgery
- psychiatry_and_psychology
- pulmonology
- test
- task_count
- 38
- task_names
- AILACasedocs
- AILAStatutes
- ArguAna-NL.v2
- CUREv1
- ConvoMem
- CovidQA
- DeepPlanning
- EPBench
- ESGReports
- FalseFriendsGermanEnglish
- GerDaLIR
- GerDaLIRSmall
- GermanDPR
- Gorilla
- KnowMeBench
- LMEBMLDR
- LMEB_SciFact
- LeCaRDv2
- LegalBenchConsumerContractsQA
- LegalBenchCorporateLobbying
- LegalQuAD
- LoCoMo
- LongMemEval
- LooGLE
- MemBench
- MemGovern
- NFCorpus-NL.v2
- NovelQA
- PeerQA
- ProceduralMemBench
- QASPER
- REALTALK
- ReMe
- SCIDOCS-NL.v2
- SciFact-NL.v2
- TMD
- ToolBench
- XMarket
- sample_size
- 241
- subset_count
- 192
- subset_sample
- Azure_azure-sdk-for-python
- Character
- ClusterHQ_flocker
- Covid-QA
- DataDog_integrations-core
- ESG-Reports
- LMEB_SciFact
- LongDepQA
- MLDR
- Meaning
- Microsoft_TypeScript
- PeerQA
- Plot
- PokemonGoF_PokemonGo-Bot
- QASPER
- Qiskit_qiskit-terra
- Relation
- Setting
- ShortDepQA
- Span
- StackStorm_st2
- Times
- ToolBench
- abstention_evidence
- adversarial
- aggregative
- apache_airflow
- apache_incubator-airflow
- appworld_qwen3_14b__generalized_query
- appworld_qwen3_32b__generalized_query
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗41.484%
- source id
- mteb
- leaderboard name
- MTEB Semantic Similarity
- dimension
- embedding
- metric
- Average task score
- rank
- 518
- sample size
- 6
- aggregation scope
- task_count
- 4
- task_names
- GermanSTSBenchmark
- SICK-NL-STS
- STS22
- STSBenchmarkMultilingualSTS
- sample_size
- 6
- subset_count
- 3
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗50.777%
- source id
- mteb
- leaderboard name
- MTEB Overall
- dimension
- embedding
- metric
- Average task score
- rank
- 561
- sample size
- 360
- aggregation scope
- splits
- all
- dentistry_and_oral_health
- dermatology
- dev
- gastroenterology
- genetics
- neuroscience_and_neurology
- orthopedic_surgery
- otorhinolaryngology
- plastic_surgery
- psychiatry_and_psychology
- pulmonology
- test
- train
- validation
- task_count
- 102
- sample_size
- 360
- subset_count
- 202
- subset_sample
- Azure_azure-sdk-for-python
- Character
- ClusterHQ_flocker
- Covid-QA
- DataDog_integrations-core
- ESG-Reports
- LMEB_SciFact
- LongDepQA
- MLDR
- Meaning
- Microsoft_TypeScript
- PeerQA
- Plot
- PokemonGoF_PokemonGo-Bot
- QASPER
- Qiskit_qiskit-terra
- Relation
- Setting
- ShortDepQA
- Span
- StackStorm_st2
- Times
- ToolBench
- abstention_evidence
- adversarial
- aggregative
- apache_airflow
- apache_incubator-airflow
- appworld_qwen3_14b__generalized_query
- appworld_qwen3_32b__generalized_query
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗36.49%
- source id
- mteb
- leaderboard name
- MTEB Classification
- dimension
- embedding
- metric
- Average task score
- rank
- 598
- sample size
- 31
- aggregation scope
- task_count
- 19
- task_names
- AmazonCounterfactualClassification
- AmazonReviewsClassification
- CovidDisinformationNLMultiLabelClassification
- DutchBookReviewSentimentClassification.v2
- DutchColaClassification
- DutchGovernmentBiasClassification
- DutchNewsArticlesClassification
- DutchSarcasticHeadlinesClassification
- IconclassClassification
- MTOPDomainClassification
- MTOPIntentClassification
- MassiveIntentClassification
- MassiveScenarioClassification
- MultiEURLEXMultilabelClassification
- MultiHateClassification
- OpenTenderClassification
- SIB200Classification
- VABBMultiLabelClassification
- VaccinChatNLClassification
- sample_size
- 31
- subset_count
- 5
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗8.17%
- source id
- mteb
- leaderboard name
- MTEB Clustering
- dimension
- embedding
- metric
- Average task score
- rank
- 687
- sample size
- 12
- aggregation scope
- task_count
- 12
- task_names
- BlurbsClusteringP2P
- BlurbsClusteringS2S
- DutchNewsArticlesClusteringP2P
- DutchNewsArticlesClusteringS2S
- IconclassClusteringS2S
- OpenTenderClusteringP2P
- OpenTenderClusteringS2S
- SIB200ClusteringS2S
- TenKGnadClusteringP2P
- TenKGnadClusteringS2S
- VABBClusteringP2P
- VABBClusteringS2S
- sample_size
- 12
- subset_count
- 2
- aggregation_method
- mean-of-task-means
- model_revision_count
- 1
- model_revision_sample
- f880174635613cff04033875fc6a69296cb72006
- source model id
- nvidia/Nemotron-3-Embed-1B-BF16
Original result ↗Published prices
1–1 / 1
$0.02
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
Provider specifications & access
1–1 / 1
- source model id
- azure-huggingface/nvidia--nemotron-3-embed-1b-bf16@1
- hosting
- foundry-managed-compute
- license
- other
- context length
- 32768
Source specification observations
1–1 / 1
- field
- context_length
- value
- 32768
- normalized value
- 32768
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models