Search public pages, research tools, and SAVRN solutions.
Open-weight model · Sentence similarity
by Nomic AI nomic-ai/nomic-embed-text-v2-moe
This model was presented in the paper Training Sparse Mixture Of Experts Text Embedding Models.
What it takes to serve nomic-embed-text-v2-moe (475M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 1.0 GB | 1.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.5 GB | 0.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Eight experts inside 475 million parameters, and the output is never a sentence: this one turns multilingual text into vectors for similarity search and RAG retrieval. Stored in float32 it is 1.9 GB on disk; at 16-bit the weights are 1.0 GB and it needs 1.1 GB to run, 0.6 GB at 8-bit, 0.3 GB at 4-bit. The cheapest hourly rate on our board, $1.85 for a single MI300X with 192 GB on-demand, turns the sizing question into documents per hour.
Apache 2.0 includes an express patent grant with the usual terms: commercial use, modification and redistribution allowed, notices kept, significant changes stated. It is derived from an unsupervised checkpoint of the same name, and one of its two papers is Matryoshka Representation Learning; read it before fixing the vector size you index. No context length is on record, so confirm the longest passage it will embed.
By Nomic AI, published under apache-2.0, revision 1066b6599d09.
Blog | Technical Report | AWS SageMaker | Atlas Embedding and Unstructured Data Analytics Platform
This model was presented in the paper Training Sparse Mixture Of Experts Text Embedding Models.
nomic-embed-text-v2-moe is a SoTA multilingual MoE text embedding model that excels at multilingual retrieval:
12 files, 1.9 GB in total. The weights are 1 file totalling 1.9 GB in safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.9 GB | 097012b27af7 |
| 1_Pooling/config.json | Configuration | 296 B | — |
| config.json | Configuration | 2.5 KB | — |
| config_sentence_transformers.json | Configuration | 554 B | — |
| modules.json | Configuration | 349 B | — |
| sentence_bert_config.json | Configuration | 53 B | — |
| special_tokens_map.json | Configuration | 964 B | — |
| README.md | Documentation | 9.1 KB | — |
| sentencepiece.bpe.model | Other | 5.1 MB | cfc8146abe2a |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | 3a56def25aa4 |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
Released by Nomic AI through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 1.9 GB |
| 16-bit | 1.0 GB |
| 8-bit | 0.5 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 1.1 GB at 16-bit and 0.3 GB at 4-bit: the weights (475M parameters) plus a working margin. A long context needs more.
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Yes. nomic-embed-text-v2-moe is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
This is a port of the LaBSE model to PyTorch. It can be used to map 109 languages to a shared vector space. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Have a look at LaBSE for the respective publication that describes LaBSE.
Semantic-Lite-2 is a lightweight multilingual sentence embedding model that produces 256-dimensional semantic vectors. It is designed for semantic search, sentence similarity, clustering, retrieval, and retrieval-augmented generation (RAG) tasks. The model is built on top of the Spark-X2.5-1.7B backbone using a frozen-backbone plus trainable-projection-head approach. The 256-dimensional output keeps vector storage compact while preserving strong retrieval quality. Vectors are L2-normalized, so cosine similarity is computed as a simple dot product. Evaluated on 500 Indonesian NLI evaluation pairs (retrieval task, chance level 0.2%): Cross-lingual evaluation (10 languages, 20 pairs per…
We introduce gte-v1.5 series, upgraded gte embeddings that support the context length of up to 8192, while further enhancing model performance. The models are built upon the transformer++ encoder backbone (BERT + RoPE + GLU). The gte-v1.5 series achieve state-of-the-art scores on the MTEB benchmark within the same model size category and prodvide competitive on the LoCo long-context retrieval tests (refer to Evaluation). We also present the gte-Qwen1.5-7B-instruct, a SOTA instruction-tuned multi-lingual embedding model that ranked 2nd in MTEB and 1st in C-MTEB. Models for Multilingual Text Retrieval](https://arxiv.org/pdf/2407.19669) Use the code below to get started with the model. It is…
12/11/2024: Release of Technical Report - 12/04/2024: Release of snowflake-arctic-embed-l-v2.0 and snowflake-arctic-embed-m-v2.0 our newest models with multilingual workloads in mind. Snowflake arctic-embed-l-v2.0 is the newest addition to the suite of embedding models Snowflake has released optimizing for retrieval performance and inference efficiency. Arctic Embed 2.0 introduces a new standard for multilingual embedding models, combining high-quality multilingual text retrieval without sacrificing performance in English. Released under the permissive Apache 2.0 license, Arctic Embed 2.0 is ideal for applications that demand reliable, enterprise-grade multilingual search and retrieval at…
This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained roberta-large model and…
This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we…