Top Embeddings
Embedding and retrieval models useful for search, RAG, semantic similarity, and local indexes.
Focused lists make the catalog useful immediately while mirror hosting remains selective and reviewed.
- Multi-Source AI Popular non-Hugging Face records from ModelScope, GitHub, arXiv, OpenML, Zenodo, Dataverse, DataCite, and other indexed open-source AI sources.
- New Open Source Recently updated public open AI artifacts across every indexed source.
How this ranks. The order uses the recorded signals described above. Runtime and verification details live on each model’s record. Self-reported evidence has no trust or ranking impact.
Mirror candidate means the files still live upstream, not on our servers yet. Hosted files do not establish a complete runnable model. Download counts, where recorded, are downloads on Hugging Face.
Showing stale catalog ·
| Type | Model | Recorded size | Downloads | Updated |
|---|---|---|---|---|
Qwen3 Embedding 0.6BQwen/Qwen3-Embedding-0.6BThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: Qwen on Hugging Face. File format: Safetensors.
| 1.21 GB | 10,189,053 downloads on Hugging Face | 2026-04-20 | |
indobert base p1indobenchmark/indobert-base-p1The catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: indobenchmark on Hugging Face. File format: BIN, H5.
| 1.65 GB | 698,084 downloads on Hugging Face | 2021-05-19 | |
Nemotron 3 Embed 1Bnvidia/Nemotron-3-Embed-1B-BF16The catalog lists this model for turning text into vectors. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for turning text into vectors.Source: nvidia on Hugging Face. File format: Safetensors.
| 2.28 GB | 665,940 downloads on Hugging Face | 2026-09-18 | |
specter2 baseallenai/specter2_baseThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: allenai on Hugging Face. File format: BIN.
| 440.7 MB | 553,728 downloads on Hugging Face | 2024-12-04 | |
gte base en v1.5Alibaba-NLP/gte-base-en-v1.5The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: Alibaba-NLP on Hugging Face. File format: Safetensors, ONNX.
| Unknown | 513,172 downloads on Hugging Face | 2024-11-15 | |
paraphrase albert small v2GPTCache/paraphrase-albert-small-v2The catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: GPTCache on Hugging Face.
| 2.07 MB | 493,211 downloads on Hugging Face | 2023-05-09 | |
llama nemotron embed 1B v2nvidia/llama-nemotron-embed-1b-v2The catalog lists this model for turning text into vectors. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for turning text into vectors.Source: nvidia on Hugging Face. File format: Safetensors, BIN.
| 4.95 GB | 438,324 downloads on Hugging Face | 2026-05-20 | |
BioLORD 2023FremyCompany/BioLORD-2023The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: FremyCompany on Hugging Face. File format: Safetensors, BIN.
| 876.9 MB | 437,365 downloads on Hugging Face | 2026-09-20 | |
sarashina embedding v1 1Bsbintuitions/sarashina-embedding-v1-1bThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: sbintuitions on Hugging Face. File format: Safetensors.
| 4.9 GB | 387,749 downloads on Hugging Face | 2026-09-20 | |
sup SimCSE VietNamese phobert baseVoVanPhuc/sup-SimCSE-VietNamese-phobert-baseThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: VoVanPhuc on Hugging Face. File format: Safetensors, BIN.
| 1.09 GB | 385,888 downloads on Hugging Face | 2026-09-20 | |
clap htsat unfusedlaion/clap-htsat-unfusedThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: laion on Hugging Face. File format: BIN.
| 617.9 MB | 366,545 downloads on Hugging Face | 2023-04-24 | |
bge multilingual gemma2BAAI/bge-multilingual-gemma2The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: BAAI on Hugging Face. File format: Safetensors.
| 37 GB | 277,660 downloads on Hugging Face | 2026-09-20 | |
ModernBERT base msmarcojoe32140/ModernBERT-base-msmarcoThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: joe32140 on Hugging Face. File format: Safetensors, ONNX.
| 2.53 GB | 272,508 downloads on Hugging Face | 2026-09-20 | |
hubert base ls960facebook/hubert-base-ls960The catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: facebook on Hugging Face. File format: BIN, H5.
| 755.3 MB | 268,571 downloads on Hugging Face | 2021-11-05 | |
Llama 2 embedding 1B 8kmesolitica/llama2-embedding-1b-8kThe catalog lists this model for finding useful details in data. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: mesolitica on Hugging Face. File format: Safetensors.
| 3.79 GB | 235,455 downloads on Hugging Face | 2026-09-20 | |
all indo e5 small v4LazarusNLP/all-indo-e5-small-v4The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: LazarusNLP on Hugging Face. File format: Safetensors, ONNX.
| 958 MB | 218,125 downloads on Hugging Face | 2026-09-20 | |
MiniLM L3 H384 uncasednreimers/MiniLM-L3-H384-uncasedThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: nreimers on Hugging Face. File format: BIN.
| 70.3 MB | 207,493 downloads on Hugging Face | 2021-08-30 | |
SapBERT UMLS 2020AB all lang from XLMRcambridgeltl/SapBERT-UMLS-2020AB-all-lang-from-XLMRThe catalog lists this model for finding useful details in data. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: cambridgeltl on Hugging Face. File format: Safetensors, BIN.
| 2.23 GB | 197,073 downloads on Hugging Face | 2026-09-20 | |
German Semantic STS V2aari1995/German_Semantic_STS_V2The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: aari1995 on Hugging Face. File format: Safetensors, BIN.
| 2.69 GB | 159,821 downloads on Hugging Face | 2026-09-20 | |
Giga Embeddings 480M 0826ai-sage/Giga-Embeddings-instruct-480M-0826The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: ai-sage on Hugging Face. File format: Safetensors.
| 967.5 MB | 154,498 downloads on Hugging Face | 2026-09-20 | |
granite speech 4.1 2B naribm-granite/granite-speech-4.1-2b-narThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: ibm-granite on Hugging Face. File format: Safetensors.
| 4.52 GB | 154,097 downloads on Hugging Face | 2026-06-18 | |
LaBSE en rucointegrated/LaBSE-en-ruThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: cointegrated on Hugging Face. File format: BIN, Safetensors, H5.
| 1.72 GB | 153,762 downloads on Hugging Face | 2026-09-20 | |
paraphrase multilingual minilm l12 v3 mngmunkhtur/paraphrase-multilingual-minilm-l12-v3-mnThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: gmunkhtur on Hugging Face. File format: Safetensors.
| 470.6 MB | 150,334 downloads on Hugging Face | 2026-09-20 | |
langcache embed v1redis/langcache-embed-v1The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: redis on Hugging Face. File format: Safetensors, ONNX, BIN.
| 1.79 GB | 149,750 downloads on Hugging Face | 2026-09-20 | |
| efficient splade VI BT large docnaver/efficient-splade-VI-BT-large-docThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed. | 287.3 MB | 127,919 downloads on Hugging Face | 2026-09-20 | |
unixcoder basemicrosoft/unixcoder-baseThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: microsoft on Hugging Face. File format: BIN.
| 505.2 MB | 126,047 downloads on Hugging Face | 2024-07-31 | |
larger clap generallaion/larger_clap_generalThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: laion on Hugging Face. File format: BIN.
| 779.8 MB | 124,117 downloads on Hugging Face | 2023-10-31 | |
st polish paraphrase from mpnetsdadas/st-polish-paraphrase-from-mpnetThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: sdadas on Hugging Face. File format: Safetensors, BIN.
| 1 GB | 117,689 downloads on Hugging Face | 2026-09-21 | |
MedCPT Query Encoderncbi/MedCPT-Query-EncoderThe catalog lists this model for finding useful details in data. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: ncbi on Hugging Face. File format: Safetensors, BIN.
| 876.9 MB | 117,659 downloads on Hugging Face | 2026-09-21 | |
bart largefacebook/bart-largeThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: facebook on Hugging Face. File format: BIN, H5.
| 5.5 GB | 109,937 downloads on Hugging Face | 2022-06-03 | |
sentence bert base ja mean tokens v2sonoisa/sentence-bert-base-ja-mean-tokens-v2The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, tags, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: sonoisa on Hugging Face. File format: Safetensors, BIN.
| 885.3 MB | 104,233 downloads on Hugging Face | 2026-09-21 | |
Nemotron 3 Embed 8Bnvidia/Nemotron-3-Embed-8B-BF16The catalog lists this model for turning text into vectors. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for turning text into vectors.Source: nvidia on Hugging Face. File format: Safetensors.
| 15.9 GB | 103,065 downloads on Hugging Face | 2026-09-21 | |
bge small zhBAAI/bge-small-zhThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: BAAI on Hugging Face. File format: BIN.
| 96.4 MB | 96,277 downloads on Hugging Face | 2023-10-12 | |
mxbai edge colbert v0 32mmixedbread-ai/mxbai-edge-colbert-v0-32mThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: mixedbread-ai on Hugging Face. File format: Safetensors, ONNX.
| 299.6 MB | 64,662 downloads on Hugging Face | 2026-08-19 | |
NV Embed v2nvidia/NV-Embed-v2The catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: nvidia on Hugging Face. File format: Safetensors.
| 15.7 GB | 44,162 downloads on Hugging Face | 2026-09-18 | |
bge m3 koreanupskyy/bge-m3-koreanThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: upskyy on Hugging Face. File format: Safetensors.
| 2.27 GB | 43,440 downloads on Hugging Face | 2026-09-21 | |
t5 base japanesesonoisa/t5-base-japaneseThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: sonoisa on Hugging Face. File format: Safetensors, BIN.
| 2.68 GB | 42,800 downloads on Hugging Face | 2026-09-21 | |
encoder e5 small v2 wikipedia relationsrelik-ie/encoder-e5-small-v2-wikipedia-relationsThe catalog lists this model for finding useful details in data. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: relik-ie on Hugging Face. File format: Safetensors.
| 133.5 MB | 41,715 downloads on Hugging Face | 2026-09-21 | |
Nemotron 3 Embed 1B AWQ W4A16groxaxo/Nemotron-3-Embed-1B-AWQ-W4A16The catalog lists this model for finding useful details in data. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: groxaxo on Hugging Face. File format: Safetensors.
| 1.04 GB | 41,574 downloads on Hugging Face | 2026-09-21 | |
mxbai edge colbert v0 17mmixedbread-ai/mxbai-edge-colbert-v0-17mThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: mixedbread-ai on Hugging Face. File format: Safetensors, ONNX.
| 156.8 MB | 37,809 downloads on Hugging Face | 2026-08-19 | |
Qwen Insuremhiveai/Qwen-InsureThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: mhiveai on Hugging Face. File format: Safetensors.
| 2.38 GB | 35,934 downloads on Hugging Face | 2026-09-21 | |
sft sql embeddings2593817/sft-sql-embeddingThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: s2593817 on Hugging Face. File format: Safetensors.
| 438 MB | 33,960 downloads on Hugging Face | 2026-09-21 | |
bekko embedding v1 a25mhotchpotch/bekko-embedding-v1-a25mThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: hotchpotch on Hugging Face. File format: Safetensors, ONNX, BIN.
| 4.31 GB | 33,044 downloads on Hugging Face | 2026-08-05 | |
Giga Embeddings 3B 0826ai-sage/Giga-Embeddings-instruct-3B-0826The catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: ai-sage on Hugging Face. File format: Safetensors.
| 6.3 GB | 32,767 downloads on Hugging Face | 2026-09-21 | |
sci rus tiny3mlsa-iai-msu-lab/sci-rus-tiny3The catalog lists this model for finding useful details in data. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: mlsa-iai-msu-lab on Hugging Face. File format: Safetensors.
| 92.2 MB | 31,927 downloads on Hugging Face | 2026-09-21 | |
BioLORD 2023 MFremyCompany/BioLORD-2023-MThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: FremyCompany on Hugging Face. File format: Safetensors, BIN.
| 2.25 GB | 31,699 downloads on Hugging Face | 2026-09-21 | |
larger clap music and speechlaion/larger_clap_music_and_speechThe catalog lists this model for finding useful details in data. Catalog sources: license, task.Content controls: not assessed.DetailsThe catalog lists this model for finding useful details in data.Source: laion on Hugging Face. File format: BIN.
| 779.8 MB | 30,989 downloads on Hugging Face | 2023-10-31 | |
llama embed nemotron 8Bnvidia/llama-embed-nemotron-8bThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: tags, task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: nvidia on Hugging Face. File format: Safetensors.
| 15 GB | 30,142 downloads on Hugging Face | 2026-09-21 | |
fine tuned column mapperabdur197/fine-tuned-column-mapperThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: abdur197 on Hugging Face. File format: Safetensors.
| 90.9 MB | 29,977 downloads on Hugging Face | 2026-09-21 | |
e5 vroyokong/e5-vThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: task.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: royokong on Hugging Face. File format: Safetensors.
| 16.7 GB | 22,015 downloads on Hugging Face | 2026-09-21 |