paraphrase-mpnet-base-v2 by Sentence Transformers

Runs On

What it takes to serve paraphrase-mpnet-base-v2 (109M 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	0.2 GB	0.3 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.1 GB	0.1 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.1 GB	0.1 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.

SAVRN's Notes on paraphrase-mpnet-base-v2

Nobody buys an accelerator for this model, and that is the point. Sentence Transformers' paraphrase-mpnet-base-v2 turns sentences and paragraphs into 768-dimensional vectors for semantic search and clustering, and at 109M parameters it needs 0.3 GB of memory at 16-bit and 0.1 GB at 8-bit or 4-bit. The cheapest listed setup is one MI300X with 192 GB at $1.85 per hour on-demand, but in practice this is the embedding stage you run on whatever card already hosts your language model.

Apache 2.0 permits commercial use, modification and redistribution, asks you to keep the notices and state significant changes, and carries a patent grant. Check two things: the 514 token context, so long documents get chunked before they are embedded, and the age of the weights, released March 2, 2022 and last updated August 19, 2025. Files ship in safetensors, ONNX, OpenVINO, PyTorch and TensorFlow.

SAVRN Research, 2026-09-18

Model Card

By Sentence Transformers, published under apache-2.0, revision 6cc9279c672d.

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.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('sentence-transformers/paraphrase-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

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.

Read the full model card (420 words)

Configuration

Architecture: MPNetModel
Context length (tokens): 514
Layers: 12
Hidden size: 768
Feed-forward size: 3,072
Attention heads: 12
Vocabulary size: 30,527
Model type: mpnet

Identity and Version

Repository: sentence-transformers/paraphrase-mpnet-base-v2
Publisher: Sentence Transformers
Task: Sentence similarity
Modality: Text
Library: sentence-transformers
Parameters: 109M parameters
Languages: tf
Revision: 6cc9279c672dc57f94445ef259b28a1b736fec8f
First published: 2022-03-02
Last updated: 2025-08-19

Files and Weights

27 files, 4.3 GB in total. The weights are 14 files totalling 4.3 GB in bin, h5, onnx, safetensors.

Weights14 files · 4.3 GB

Configuration6 files · 1.4 KB

Tokenizer3 files · 698.9 KB

Documentation1 file · 4.7 KB

Other2 files · 1.2 MB

Repository1 file · 744 B

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	438.0 MB	5fc2279bd6e5
onnx/model.onnx	Weights	435.8 MB	eeb223188121
onnx/model_O1.onnx	Weights	435.7 MB	32e665c709aa
onnx/model_O2.onnx	Weights	435.7 MB	813b36389099
onnx/model_O3.onnx	Weights	435.7 MB	11d4b1a935b5
onnx/model_O4.onnx	Weights	217.9 MB	2483512b4e72
onnx/model_qint8_arm64.onnx	Weights	110.1 MB	a68ae94426f6
onnx/model_qint8_avx512.onnx	Weights	110.1 MB	a68ae94426f6
onnx/model_qint8_avx512_vnni.onnx	Weights	110.1 MB	a68ae94426f6
onnx/model_quint8_avx2.onnx	Weights	110.2 MB	47f16f7937cf
openvino/openvino_model.bin	Weights	435.6 MB	5760db46508f
openvino/openvino_model_qint8_quantized.bin	Weights	110.0 MB	5e53de5c6081
pytorch_model.bin	Weights	438.0 MB	6c5e122fb260
tf_model.h5	Weights	438.2 MB	2805a066aca7
1_Pooling/config.json	Configuration	190 B	—
config.json	Configuration	594 B	—
config_sentence_transformers.json	Configuration	122 B	—
modules.json	Configuration	229 B	—
sentence_bert_config.json	Configuration	53 B	—
special_tokens_map.json	Configuration	239 B	—
README.md	Documentation	4.7 KB	—
openvino/openvino_model.xml	Other	432.8 KB	—
openvino/openvino_model_qint8_quantized.xml	Other	741.9 KB	—
.gitattributes	Repository	744 B	—
tokenizer.json	Tokenizer	466.2 KB	—
tokenizer_config.json	Tokenizer	1.2 KB	—
vocab.txt	Tokenizer	231.5 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 4.3 GB

Download from Sentence Transformers

Released by Sentence Transformers through its official repository on Hugging Face. Read the license.

Built From

Described by arXiv:1908.10084

Memory Requirements

Precision	Weights in memory
As published	4.3 GB
16-bit	0.2 GB
8-bit	0.1 GB
4-bit	0.1 GB

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

Compare paraphrase-mpnet-base-v2

all-mpnet-base-v2 vs paraphrase-mpnet-base-v2

Questions About paraphrase-mpnet-base-v2

How much GPU memory does paraphrase-mpnet-base-v2 need?

About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (109M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run paraphrase-mpnet-base-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 paraphrase-mpnet-base-v2 commercially?

Yes. paraphrase-mpnet-base-v2 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.

What is paraphrase-mpnet-base-v2's context length?

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

Similar Models

Model · Sentence similarity

all-mpnet-base-v2

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 109M parameters 514 tokens sentence-transformers

View model

Model · Sentence similarity

multi-qa-mpnet-base-dot-v1

Sentence Transformers

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for semantic search. It has been trained on 215M (question, answer) pairs from diverse sources. For an introduction to semantic search, have a look at: SBERT.net - 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 correct pooling-operation on-top of the contextualized word embeddings. Text Embeddings Inference (TEI) is a blazing fast…

Open weights 109M parameters 514 tokens sentence-transformers

View model

Model · Sentence similarity

nli-mpnet-base-v2

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 109M parameters 514 tokens sentence-transformers

View model

Model · Sentence similarity

lt-wikidata-comp-en

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 109M parameters 514 tokens sentence-transformers

View model

Model · Sentence similarity

lt-un-data-fine-fine-en

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 109M parameters 514 tokens sentence-transformers

View model

Model · Sentence similarity

names-linking-model

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 109M parameters 514 tokens sentence-transformers

View model