# multilingual-e5-base by Liang Wang: Open-Weight Model
Source: https://savrn.com/models/multilingual-e5-base
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve multilingual-e5-base (278M 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 | 0.6 GB | 0.7 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 | 0.3 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 |
| 4-bit | 0.1 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 23, 2026.

[multilingual-e5-base on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/multilingual-e5-base/gpus)

## SAVRN's Notes on multilingual-e5-base

Seven tenths of a gigabyte is the whole footprint at 16-bit, on a card that holds 192 GB. That is multilingual-e5-base, a 278M-parameter sentence-similarity model. Nobody dedicates an MI300X at $1.85 an hour to 0.7 GB; you run it beside other work on a card you already own, or drop to 8-bit and 0.3 GB. Disk is another matter: 23 files and 5.3 GB, because the repository carries safetensors, ONNX, OpenVINO and PyTorch copies, and you need one.

MIT is about as short as licenses get: commercial use, modification and redistribution, provided the copyright and permission notices travel with the files. Context is 514 tokens, so long passages get chunked before encoding. The publisher initialized it from xlm-roberta-base and continually trained it on multilingual data, covering 100 languages with degradation possible in low-resource ones, so test yours first. Weights are stored in float32; the 16-bit figure assumes you convert.

SAVRN Research, 2026-09-18

## Model Card

By Liang Wang, published under mit, revision d12875059715.

[Multilingual E5 Text Embeddings: A Technical Report](https://savrn.com/papers/multilingual-e5-text-embeddings-a-technical-report). Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024

This model has 12 layers and the embedding size is 768.

### Usage

Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.

[Read the full model card (900 words)](https://savrn.com/models/multilingual-e5-base/card)

## Configuration

Architecture

XLMRobertaModel

Context length (tokens)

514

Layers

12

Hidden size

768

Feed-forward size

3,072

Attention heads

12

Vocabulary size

250,002

Stored precision

float32

Model type

xlm-roberta

## Identity and Version

Repository

intfloat/multilingual-e5-base

Publisher

Liang Wang

Task

Sentence similarity

Modality

Text

Library

sentence-transformers

Parameters

278M parameters

Languages

af, am, ar, as, az, be, bg, bn

Revision

d128750597153bb5987e10b1c3493a34e5a4502a

First published

2023-05-19

Last updated

2026-04-02

## Files and Weights

23 files, 5.3 GB in total. The weights are 6 files totalling 5.3 GB in bin, onnx, safetensors.

Weights6 files · 5.3 GB

Configuration8 files · 3.2 KB

Tokenizer4 files · 34.2 MB

Documentation1 file · 179.3 KB

Other3 files · 10.5 MB

Repository1 file · 1.5 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model.safetensors | Weights | 1.1 GB | a18a44fad1d0 |
| onnx/model.onnx | Weights | 1.1 GB | 84a4d426f7e8 |
| onnx/model_O4.onnx | Weights | 554.9 MB | f60256a833ca |
| onnx/model_qint8_avx512_vnni.onnx | Weights | 278.7 MB | 252355187865 |
| openvino/openvino_model.bin | Weights | 1.1 GB | 116c03a2814d |
| pytorch_model.bin | Weights | 1.1 GB | f061cb764188 |
| .eval_results/ArguAna.yaml | Configuration | 575 B | — |
| 1_Pooling/config.json | Configuration | 200 B | — |
| config.json | Configuration | 694 B | — |
| modules.json | Configuration | 387 B | — |
| onnx/config.json | Configuration | 686 B | — |
| onnx/special_tokens_map.json | Configuration | 280 B | — |
| sentence_bert_config.json | Configuration | 57 B | — |
| special_tokens_map.json | Configuration | 280 B | — |
| README.md | Documentation | 179.3 KB | — |
| onnx/sentencepiece.bpe.model | Other | 5.1 MB | cfc8146abe2a |
| openvino/openvino_model.xml | Other | 367.7 KB | — |
| sentencepiece.bpe.model | Other | 5.1 MB | cfc8146abe2a |
| .gitattributes | Repository | 1.5 KB | — |
| onnx/tokenizer.json | Tokenizer | 17.1 MB | 62c24cdc13d4 |
| onnx/tokenizer_config.json | Tokenizer | 418 B | — |
| tokenizer.json | Tokenizer | 17.1 MB | 62c24cdc13d4 |
| tokenizer_config.json | Tokenizer | 418 B | — |

## License and Download

License

mit

Access

Open weights, no gate

Download size

5.3 GB

[Download from Liang Wang](https://huggingface.co/intfloat/multilingual-e5-base)

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:2108.08787](https://savrn.com/papers/mr-tydi-a-multi-lingual-benchmark-for-dense-retrieval)
- Described by [arXiv:2210.07316](https://savrn.com/papers/mteb-massive-text-embedding-benchmark)
- Described by [arXiv:2402.05672](https://savrn.com/papers/multilingual-e5-text-embeddings-a-technical-report)

## 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 (de) | Configuration deTask ClassificationMetric accuracyComparison conditions not established | 71.7238 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (de) | Configuration deTask ClassificationMetric apComparison conditions not established | 82.2209 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (de) | Configuration deTask ClassificationMetric f1Comparison conditions not established | 69.9553 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 78.9701 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 43.6935 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 73.3808 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric accuracyComparison conditions not established | 79.6552 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric apComparison conditions not established | 28.5079 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric f1Comparison conditions not established | 66.8452 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (ja) | Configuration jaTask ClassificationMetric accuracyComparison conditions not established | 73.3298 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (ja) | Configuration jaTask ClassificationMetric apComparison conditions not established | 20.7205 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (ja) | Configuration jaTask ClassificationMetric f1Comparison conditions not established | 59.78 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 90.6377 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric apComparison conditions not established | 87.2228 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 90.6038 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (de) | Configuration deTask ClassificationMetric accuracyComparison conditions not established | 41.828 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (de) | Configuration deTask ClassificationMetric f1Comparison conditions not established | 41.271 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 44.546 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 44.0567 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (es) | Configuration esTask ClassificationMetric accuracyComparison conditions not established | 40.534 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (es) | Configuration esTask ClassificationMetric f1Comparison conditions not established | 39.8207 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (fr) | Configuration frTask ClassificationMetric accuracyComparison conditions not established | 39.684 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (fr) | Configuration frTask ClassificationMetric f1Comparison conditions not established | 39.1105 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (ja) | Configuration jaTask ClassificationMetric accuracyComparison conditions not established | 37.436 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (ja) | Configuration jaTask ClassificationMetric f1Comparison conditions not established | 37.0708 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (zh) | Configuration zhTask ClassificationMetric accuracyComparison conditions not established | 37.226 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (zh) | Configuration zhTask ClassificationMetric f1Comparison conditions not established | 36.6537 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 22.831 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 36.42 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 37.699 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 37.724 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 32.207 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 34.312 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1Comparison conditions not established | 23.257 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_10Comparison conditions not established | 36.574 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_100Comparison conditions not established | 37.854 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1000Comparison conditions not established | 37.878 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_3Comparison conditions not established | 32.385 | [intfloat](https://huggingface.co/intfloat/multilingual-e5-base) Publisher reported | Evaluated revision not stated | — |
| mteb/arguana | Task ArguAnaMetric ArguAnaSetup Obtained using MTEB v1.12.75Comparison conditions not established | 44.206 | [Obtained using MTEB v1.12.75](https://github.com/embeddings-benchmark/mteb/) Reported by a third party | Evaluated revision not stated | 2026-04-02 |
| mteb/arguana | Task ArguAna_default_testMetric ArguAna_default_testSetup Obtained using MTEB v1.12.75Comparison conditions not established | 44.206 | [Obtained using MTEB v1.12.75](https://github.com/embeddings-benchmark/mteb/) Reported by a third party | Evaluated revision not stated | 2026-04-02 |

## Memory Requirements

| Precision | Weights in memory |
| --- | --- |
| As published | 5.3 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 GB |

Weights only, from the published parameter count; the key-value cache and runtime add to this.

## Built on This Model

- Derived from[multilingual-intent-router](https://savrn.com/models/multilingual-intent-router)
- Derived from[text2ipc-pt](https://savrn.com/models/text2ipc-pt)

## Compare multilingual-e5-base

- [multilingual-e5-base vs paraphrase-multilingual-mpnet-base-v2](https://savrn.com/models/compare/multilingual-e5-base-vs-paraphrase-multilingual-mpnet-base-v2)
- [embeddinggemma-300m vs multilingual-e5-base](https://savrn.com/models/compare/embeddinggemma-300m-vs-multilingual-e5-base)
- [gte-multilingual-base vs multilingual-e5-base](https://savrn.com/models/compare/gte-multilingual-base-vs-multilingual-e5-base)

## Questions About multilingual-e5-base

### How much GPU memory does multilingual-e5-base need?

About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (278M parameters) plus a working margin. A long context needs more.

### What is the cheapest GPU to run multilingual-e5-base 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 multilingual-e5-base commercially?

Yes. multilingual-e5-base 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 multilingual-e5-base's context length?

514 tokens, from the maximum position embeddings in its published configuration.

## Similar Models

Model · Sentence similarity

### [paraphrase-multilingual-mpnet-base-v2](https://savrn.com/models/paraphrase-multilingual-mpnet-base-v2)

[Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers)

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 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. Text Embeddings Inference (TEI) is a blazing fast inference solution for text embedding models. Send a request to /v1/embeddings to generate embeddings via the OpenAI Embeddings API: Or check…

Open weights apache-2.0 278M parameters 514 tokens sentence-transformers

[View model](https://savrn.com/models/paraphrase-multilingual-mpnet-base-v2)

Model · Sentence similarity

### [lt-wikidata-comp-multi](https://savrn.com/models/lt-wikidata-comp-multi)

[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 768 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 278M parameters 514 tokens sentence-transformers

[View model](https://savrn.com/models/lt-wikidata-comp-multi)

Model · Sentence similarity

### [lt-un-data-fine-industry-multi](https://savrn.com/models/lt-un-data-fine-industry-multi)

[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 768 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 278M parameters 514 tokens sentence-transformers

[View model](https://savrn.com/models/lt-un-data-fine-industry-multi)

Model · Sentence similarity

### [lt-un-data-fine-fine-multi](https://savrn.com/models/lt-un-data-fine-fine-multi)

[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 768 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 278M parameters 514 tokens sentence-transformers

[View model](https://savrn.com/models/lt-un-data-fine-fine-multi)

Model · Sentence similarity

### [lt-un-data-fine-coarse-multi](https://savrn.com/models/lt-un-data-fine-coarse-multi)

[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 768 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 278M parameters 514 tokens sentence-transformers

[View model](https://savrn.com/models/lt-un-data-fine-coarse-multi)

Model · Sentence similarity

### [embeddinggemma-300m](https://savrn.com/models/embeddinggemma-300m)

[Google](https://savrn.com/model-publishers/google)

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages. The small size and on-device focus makes it possible to deploy in environments with limited resources such as mobile phones, laptops, or desktops, democratizing access to state of the art AI models and helping foster innovation for everyone.…

Access requested at publisher gemma 303M parameters sentence-transformers

[View model](https://savrn.com/models/embeddinggemma-300m)

## Liang Wang

[All models and datasets](https://savrn.com/model-publishers/intfloat)

## Versions

- [d12875059715](https://savrn.com/models/multilingual-e5-base/versions/d12875059715) · current 2026-10-23

## 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/multilingual-e5-base)
- [How the hub is built](https://savrn.com/model-hub/methodology)