# e5-large-v2 by Liang Wang: Open-Weight Model Source: https://savrn.com/models/e5-large-v2 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve e5-large-v2 (335M 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 | 0.7 GB | 0.8 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 | 0.3 GB | 0.4 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 | 0.2 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 22, 2026. [e5-large-v2 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/e5-large-v2/gpus) ## SAVRN's Notes on e5-large-v2 The download and the working set are different sizes. The repository is 6.7 GB across 20 files because the weights are stored in float32 and shipped in four formats, safetensors, onnx, openvino and pytorch, while the 16-bit working set is 0.7 GB of weights in 0.8 GB of memory. Our Index lists a single MI300X at $1.85 per hour as the cheapest fit, but 192 GB is far more card than a 335M-parameter BERT encoder needs; the practical home is a slice of a machine already doing other work. MIT terms are the easiest to clear: commercial use, modification and redistribution with the notices kept, so legal review is short. Before committing, read the publisher's note on whether to add the query and passage prefixes to inputs, and settle that before anything is benchmarked. Context is 512 tokens. Released in May 2023, it still draws 1,637,946 downloads a month. SAVRN Research, 2026-09-18 ## Model Card By Liang Wang, published under mit, revision f169b11e22de. [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://savrn.com/papers/text-embeddings-by-weakly-supervised-contrastive-pre-training). Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022 This model has 24 layers and the embedding size is 1024. ### Usage Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. [Read the full model card (682 words)](https://savrn.com/models/e5-large-v2/card) ## Configuration Architecture BertModel Context length (tokens) 512 Layers 24 Hidden size 1,024 Feed-forward size 4,096 Attention heads 16 Vocabulary size 30,522 Stored precision float32 Model type bert ## Identity and Version Repository intfloat/e5-large-v2 Publisher Liang Wang Task Sentence similarity Modality Text Library sentence-transformers Parameters 335M parameters Languages en Revision f169b11e22de13617baa190a028a32f3493550b6 First published 2023-05-19 Last updated 2025-02-17 ## Files and Weights 20 files, 6.7 GB in total. The weights are 7 files totalling 6.7 GB in bin, onnx, safetensors. Weights7 files · 6.7 GB Configuration6 files · 2.5 KB Tokenizer3 files · 943.2 KB Documentation1 file · 67.8 KB Other2 files · 2.0 MB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 1.3 GB | d741c1a688a6 | | onnx/model.onnx | Weights | 1.3 GB | f560bbc5da58 | | onnx/model_O4.onnx | Weights | 668.5 MB | 4ed58868e4b3 | | onnx/model_qint8_avx512_vnni.onnx | Weights | 337.2 MB | 40be69cbaec2 | | openvino/openvino_model.bin | Weights | 1.3 GB | e1c8fee29a7e | | openvino/openvino_model_qint8_quantized.bin | Weights | 336.8 MB | 763705b01203 | | pytorch_model.bin | Weights | 1.3 GB | 7d3fda358533 | | 1_Pooling/config.json | Configuration | 201 B | — | | config.json | Configuration | 616 B | — | | handler.py | Configuration | 1.1 KB | — | | modules.json | Configuration | 387 B | — | | sentence_bert_config.json | Configuration | 57 B | — | | special_tokens_map.json | Configuration | 125 B | — | | README.md | Documentation | 67.8 KB | — | | openvino/openvino_model.xml | Other | 707.8 KB | — | | openvino/openvino_model_qint8_quantized.xml | Other | 1.3 MB | — | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.json | Tokenizer | 711.4 KB | — | | tokenizer_config.json | Tokenizer | 314 B | — | | vocab.txt | Tokenizer | 231.5 KB | — | ## License and Download License mit Access Open weights, no gate Download size 6.7 GB [Download from Liang Wang](https://huggingface.co/intfloat/e5-large-v2) Released by Liang Wang through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Described by [arXiv:2104.08663](https://savrn.com/papers/beir-a-heterogenous-benchmark-for-zero-shot-evaluation-of-information-retrieval-models) - Described by [arXiv:2210.07316](https://savrn.com/papers/mteb-massive-text-embedding-benchmark) - Described by [arXiv:2212.03533](https://savrn.com/papers/text-embeddings-by-weakly-supervised-contrastive-pre-training) ## Evaluations Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical. | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 79.2239 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 43.2082 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 73.2781 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 93.7483 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric apComparison conditions not established | 90.7253 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 93.739 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 48.612 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 47.6116 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 23.542 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 38.208 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 39.417 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 39.429 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 33.95 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 36.329 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1Comparison conditions not established | 23.755 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_10Comparison conditions not established | 38.288 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_100Comparison conditions not established | 39.511 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1000Comparison conditions not established | 39.523 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_3Comparison conditions not established | 34.009 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_5Comparison conditions not established | 36.434 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1Comparison conditions not established | 23.542 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_10Comparison conditions not established | 46.417 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_100Comparison conditions not established | 51.812 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1000Comparison conditions not established | 52.137 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_3Comparison conditions not established | 37.528 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_5Comparison conditions not established | 41.81 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1Comparison conditions not established | 23.542 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_10Comparison conditions not established | 7.269 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_100Comparison conditions not established | 0.969 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1000Comparison conditions not established | 0.099 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_3Comparison conditions not established | 15.979 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_5Comparison conditions not established | 11.664 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1Comparison conditions not established | 23.542 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_10Comparison conditions not established | 72.688 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_100Comparison conditions not established | 96.871 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1000Comparison conditions not established | 99.431 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_3Comparison conditions not established | 47.937 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_5Comparison conditions not established | 58.321 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArxivClusteringP2P | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 45.5465 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | | MTEB ArxivClusteringS2S | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 41.0161 | [intfloat](https://huggingface.co/intfloat/e5-large-v2) Publisher reported | Evaluated revision not stated | — | ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 6.7 GB | | 16-bit | 0.7 GB | | 8-bit | 0.3 GB | | 4-bit | 0.2 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About e5-large-v2 ### How much GPU memory does e5-large-v2 need? About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (335M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run e5-large-v2 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 e5-large-v2 commercially? Yes. e5-large-v2 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included. ### What is e5-large-v2's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Sentence similarity ### [gte-large](https://savrn.com/models/gte-large) [Dingkun Long](https://savrn.com/model-publishers/thenlper) General Text Embeddings (GTE) model. Towards General Text Embeddings with Multi-stage Contrastive Learning The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc. We compared the performance of the GTE models with other popular text embedding models on the MTEB… Open weights mit 335M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/gte-large) Model · Sentence similarity ### [KielEmbed-Pro](https://savrn.com/models/kielembed-pro) [Tech](https://savrn.com/model-publishers/kiel2) This is a sentence-transformers model finetuned from BAAI/bge-large-en-v1.5. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval. First install the Sentence Transformers library: Then you can load this model and run inference. Approximate statistics based on the first 1000 samples: - perdevicetrainbatchsize: 2 - gradientaccumulationsteps: 16 - learningrate: 2e-05 - numtrainepochs: 1 - warmupsteps: 0.1 - fp16: True - gradientcheckpointing: True - dopredict: False - predictionlossonly: True - perdevicetrainbatchsize: 2 - perdeviceevalbatchsize: 8 - gradientaccumulationsteps: 16 - evalaccumulationsteps: None - torchemptycachesteps: None… Open weights 335M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/kielembed-pro) Model · Sentence similarity ### [lt-wikidata-comp-de](https://savrn.com/models/lt-wikidata-comp-de) [Dell Research Harvard](https://savrn.com/model-publishers/dell-research-harvard) 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… Open weights mit 336M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/lt-wikidata-comp-de) Model · Sentence similarity ### [lt-un-data-fine-fine-fr](https://savrn.com/models/lt-un-data-fine-fine-fr) [Dell Research Harvard](https://savrn.com/model-publishers/dell-research-harvard) 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… Open weights 337M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/lt-un-data-fine-fine-fr) 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) Model · Sentence similarity ### [gte-multilingual-base](https://savrn.com/models/gte-multilingual-base) [Alibaba-NLP](https://savrn.com/model-publishers/alibaba-nlp) The gte-multilingual-base model is the latest in the GTE (General Text Embedding) family of models, featuring several key attributes: Paper: mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval - It is recommended to install xformers and enable unpadding for acceleration, refer to enable-unpadding-and-xformers. - How to use with TEI: refs/pr/7 Usage via docker and infinity, MIT Licensed. Usage via Docker and Text Embeddings Inference (TEI): Then you can send requests to the deployed API via the OpenAI-compatible v1/embeddings route (more information about the OpenAI Embeddings API): We validated the performance of the gte-multilingual-base… Open weights apache-2.0 305M parameters 8,192 tokens sentence-transformers [View model](https://savrn.com/models/gte-multilingual-base) ## Liang Wang [All models and datasets](https://savrn.com/model-publishers/intfloat) ## Versions - [f169b11e22de](https://savrn.com/models/e5-large-v2/versions/f169b11e22de) · current 2026-10-18 ## Explore More - [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity) - [All models under mit](https://savrn.com/models/licenses/mit) - [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. - [Liang Wang website](https://github.com/microsoft/unilm/tree/master/e5) - [Hugging Face record](https://huggingface.co/intfloat/e5-large-v2) - [How the hub is built](https://savrn.com/model-hub/methodology)