# nomic-embed-text-v2-moe by Nomic AI: Open-Weight Model Source: https://savrn.com/models/nomic-embed-text-v2-moe Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On 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](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.5 GB | 0.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.2 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [nomic-embed-text-v2-moe on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/nomic-embed-text-v2-moe/gpus) ## SAVRN's Notes on nomic-embed-text-v2-moe 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. SAVRN Research, 2026-09-18 ## Model Card By Nomic AI, published under apache-2.0, revision 1066b6599d09. ### nomic-embed-text-v2-moe: Multilingual Mixture of Experts Text Embeddings [Blog](https://www.nomic.ai/blog/posts/nomic-embed-text-v2) | [Technical Report](https://huggingface.co/papers/2502.07972) | [AWS SageMaker](https://aws.amazon.com/marketplace/seller-profile?id=seller-tpqidcj54zawi) | [Atlas Embedding and Unstructured Data Analytics Platform](https://atlas.nomic.ai) This model was presented in the paper [Training Sparse Mixture Of Experts Text Embedding Models](https://huggingface.co/papers/2502.07972). ### Model Overview nomic-embed-text-v2-moe is a SoTA multilingual MoE text embedding model that excels at multilingual retrieval: - High Performance: SoTA Multilingual performance compared to ~300M parameter models, competitive with models 2x in size - Multilinguality: Supports ~100 languages and trained on over 1.6B pairs - Flexible Embedding Dimension: Trained with [Matryoshka Embeddings](https://savrn.com/papers/matryoshka-representation-learning) with 3x reductions in storage cost with minimal performance degradations - Fully Open-Source: Model weights, [code](https://github.com/nomic-ai/contrastors), and training data (see code repo) released [Read the full model card (814 words)](https://savrn.com/models/nomic-embed-text-v2-moe/card) ## Configuration Architecture NomicBertModel Vocabulary size 250,048 Experts 8 Stored precision float32 Model type nomic_bert ## Identity and Version Repository nomic-ai/nomic-embed-text-v2-moe Publisher Nomic AI Task Sentence similarity Modality Text Library sentence-transformers Parameters 475M parameters Languages en, es, fr, de, it, pt, pl, nl Revision 1066b6599d099fbb93dfcb64f9c37a7c9e503e85 First published 2025-02-07 Last updated 2025-04-01 ## Files and Weights 12 files, 1.9 GB in total. The weights are 1 file totalling 1.9 GB in safetensors. Weights1 file · 1.9 GB Configuration6 files · 4.7 KB Tokenizer2 files · 17.1 MB Documentation1 file · 9.1 KB Other1 file · 5.1 MB Repository1 file · 1.6 KB Every file | 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 | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 1.9 GB [Download from Nomic AI](https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe) Released by Nomic AI through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from nomic-ai/nomic-embed-text-v2-moe-unsupervised - Described by [arXiv:2205.13147](https://savrn.com/papers/matryoshka-representation-learning) - Described by arXiv:2502.07972 ## Memory Requirements | 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. ## Questions About nomic-embed-text-v2-moe ### How much GPU memory does nomic-embed-text-v2-moe need? 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. ### What is the cheapest GPU to run nomic-embed-text-v2-moe on? 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. ### Can I use nomic-embed-text-v2-moe commercially? 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. ## Similar Models Model · Sentence similarity ### [LaBSE](https://savrn.com/models/labse) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) 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. Open weights apache-2.0 471M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/labse) Model · Sentence similarity ### [semantic-lite-2](https://savrn.com/models/semantic-lite-2) [Zulfah](https://savrn.com/model-publishers/ukung) 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… Open weights apache-2.0 460M parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/semantic-lite-2) Model · Sentence similarity ### [gte-large-en-v1.5](https://savrn.com/models/gte-large-en-v1-5) [Alibaba-NLP](https://savrn.com/model-publishers/alibaba-nlp) 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… Open weights apache-2.0 434M parameters 8,192 tokens transformers [View model](https://savrn.com/models/gte-large-en-v1-5) Model · Sentence similarity ### [snowflake-arctic-embed-l-v2.0](https://savrn.com/models/snowflake-arctic-embed-l-v2-0) [Snowflake](https://savrn.com/model-publishers/snowflake) 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… Open weights apache-2.0 568M parameters 8,194 tokens sentence-transformers [View model](https://savrn.com/models/snowflake-arctic-embed-l-v2-0) Model · Sentence similarity ### [ateneo-bge-m3-ecuador-v2](https://savrn.com/models/ateneo-bge-m3-ecuador-v2) [Jorge Doicela](https://savrn.com/model-publishers/doiceladev) This is a sentence-transformers model finetuned from BAAI/bge-m3. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more. First install the Sentence Transformers library: Then you can load this model and run inference. Evaluated with InformationRetrievalEvaluator Approximate statistics based on the first 100 samples: - perdevicetrainbatchsize: 32 - numtrainepochs: 5 - learningrate: 2e-05 - lrschedulertype: cosine - warmupsteps: 0.1 - optim: adamwtorch - weightdecay: 0.01 - bf16: True - perdeviceevalbatchsize: 32 - loadbestmodelatend: True… Open weights 568M parameters 8,194 tokens sentence-transformers [View model](https://savrn.com/models/ateneo-bge-m3-ecuador-v2) Model · Sentence similarity ### [all-roberta-large-v1](https://savrn.com/models/all-roberta-large-v1) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) 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… Open weights apache-2.0 355M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/all-roberta-large-v1) ## Nomic AI [All models and datasets](https://savrn.com/model-publishers/nomic-ai) ## Versions - [1066b6599d09](https://savrn.com/models/nomic-embed-text-v2-moe/versions/1066b6599d09) · current 2026-10-24 ## Explore More - [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Nomic AI website](https://www.nomic.ai/) - [Hugging Face record](https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe) - [How the hub is built](https://savrn.com/model-hub/methodology)