paraphrase-MiniLM-L3-v2 by Sentence Transformers: Open Model

Runs On

What it takes to serve paraphrase-MiniLM-L3-v2 (17M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Cheapest setup	Per hour	Also fits
16-bit	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	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-MiniLM-L3-v2

Three layers is the whole story here. Sentence Transformers built this 17M-parameter model to turn sentences and paragraphs into 384-dimensional vectors for clustering and semantic search, and the memory figures on this page round to 0.0 GB at 16-bit, 8-bit and 4-bit. The cheapest listed host, one MI300X with 192 GB at $1.85 an hour on-demand, is a card you share with everything else in the rack; the question is what runs beside it, not whether it fits.

Apache 2.0 permits commercial use, modification and redistribution; keep the license, copyright notices and any NOTICE file with it and state significant changes. Check the 512-token context, which means long documents get chunked before embedding, and read the eight training sets, ms_marco, snli and multi_nli among them, against your own corpus. No Index host prices it per token, so running it yourself is the only cost we can show.

SAVRN Research, 2026-09-18

Model Card

By Sentence Transformers, published under apache-2.0, revision 4ca70771034a.

This is a sentence-transformers model: It maps sentences & paragraphs to a 384 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-MiniLM-L3-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 (316 words)

Configuration

Architecture: BertModel
Context length (tokens): 512
Layers: 3
Hidden size: 384
Feed-forward size: 1,536
Attention heads: 12
Vocabulary size: 30,522
Model type: bert

Identity and Version

Repository: sentence-transformers/paraphrase-MiniLM-L3-v2
Publisher: Sentence Transformers
Task: Sentence similarity
Modality: Text
Library: sentence-transformers
Parameters: 17M parameters
Languages: tf
Revision: 4ca70771034acceecb2e72475f72050fcdde4ddc
First published: 2022-03-02
Last updated: 2025-03-06

Files and Weights

27 files, 676.8 MB in total. The weights are 14 files totalling 675.8 MB in bin, h5, onnx, safetensors.

Weights14 files · 675.8 MB

Configuration6 files · 1.3 KB

Tokenizer3 files · 698.1 KB

Documentation1 file · 3.8 KB

Other2 files · 317.5 KB

Repository1 file · 744 B

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	69.6 MB	cf1e4e2d420c
onnx/model.onnx	Weights	69.0 MB	84007b609c7a
onnx/model_O1.onnx	Weights	69.0 MB	9af6e4395562
onnx/model_O2.onnx	Weights	69.0 MB	2312521d80b6
onnx/model_O3.onnx	Weights	69.0 MB	b0cd24e08220
onnx/model_O4.onnx	Weights	34.5 MB	48881b7e13a8
onnx/model_qint8_arm64.onnx	Weights	17.5 MB	44a2d6852c28
onnx/model_qint8_avx512.onnx	Weights	17.5 MB	44a2d6852c28
onnx/model_qint8_avx512_vnni.onnx	Weights	17.5 MB	44a2d6852c28
onnx/model_quint8_avx2.onnx	Weights	17.5 MB	7b411e18f597
openvino/openvino_model.bin	Weights	69.0 MB	75e687f460e4
openvino/openvino_model_qint8_quantized.bin	Weights	17.5 MB	fb8f0df8d317
pytorch_model.bin	Weights	69.6 MB	6b0a1c48c249
tf_model.h5	Weights	69.6 MB	e5ecd112cca8
1_Pooling/config.json	Configuration	190 B	—
config.json	Configuration	629 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	112 B	—
README.md	Documentation	3.8 KB	—
openvino/openvino_model.xml	Other	118.2 KB	—
openvino/openvino_model_qint8_quantized.xml	Other	199.3 KB	—
.gitattributes	Repository	744 B	—
tokenizer.json	Tokenizer	466.2 KB	—
tokenizer_config.json	Tokenizer	314 B	—
vocab.txt	Tokenizer	231.5 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 675.8 MB

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
Trained on (disclosed) embedding-data/QQP
Trained on (disclosed) embedding-data/altlex
Trained on (disclosed) embedding-data/coco_captions
Trained on (disclosed) embedding-data/flickr30k-captions
Trained on (disclosed) embedding-data/sentence-compression
Trained on (disclosed) embedding-data/simple-wiki
Trained on (disclosed) flax-sentence-embeddings/stackexchange_xml
Trained on (disclosed) ms_marco
Trained on (disclosed) multi_nli
Trained on (disclosed) s2orc
Trained on (disclosed) snli
Trained on (disclosed) wiki_atomic_edits
Trained on (disclosed) yahoo_answers_topics

Memory Requirements

Precision	Weights in memory
As published	675.8 MB
16-bit	0.0 GB
8-bit	0.0 GB
4-bit	0.0 GB

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

Questions About paraphrase-MiniLM-L3-v2

How much GPU memory does paraphrase-MiniLM-L3-v2 need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (17M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run paraphrase-MiniLM-L3-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-MiniLM-L3-v2 commercially?

Yes. paraphrase-MiniLM-L3-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-MiniLM-L3-v2's context length?

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

Similar Models

Model · Sentence similarity

bge-micro-v2

Taylor

This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Distilled in a 2-step training process (bge-micro was step 1) from BAAI/bge-small-en-v1.5. 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. For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Open weights mit 17M parameters 512 tokens sentence-transformers

View model

Model · Sentence similarity

all-MiniLM-L6-v2

Sentence Transformers

This is a sentence-transformers model: It maps sentences & paragraphs to a 384 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…

Open weights apache-2.0 23M parameters 512 tokens sentence-transformers

View model

Model · Sentence similarity

paraphrase-MiniLM-L6-v2

Sentence Transformers

This is a sentence-transformers model: It maps sentences & paragraphs to a 384 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. This model was trained by sentence-transformers. If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Open weights apache-2.0 23M parameters 512 tokens sentence-transformers

View model

Model · Sentence similarity

multi-qa-MiniLM-L6-cos-v1

Sentence Transformers

This is a sentence-transformers model: It maps sentences & paragraphs to a 384 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. Similarly to the PyTorch example above, to use the model…

Open weights 23M parameters 512 tokens sentence-transformers

View model

Model · Sentence similarity

paraphrase-albert-small-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. This model was trained by sentence-transformers. If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Open weights apache-2.0 12M parameters 512 tokens sentence-transformers

View model

Model · Sentence similarity

rubert-tiny2

David Dale

This is an updated version of cointegrated/rubert-tiny: a small Russian BERT-based encoder with high-quality sentence embeddings. This post in Russian gives more details. The differences from the previous version include: - sentence embeddings approximate LaBSE closer than before; - meaningful segment embeddings (tuned on the NLI task) - the model is focused only on Russian. The model should be used as is to produce sentence embeddings (e.g. for KNN classification of short texts) or fine-tuned for a downstream task. Sentence embeddings can be produced as follows: Alternatively, you can use the model with sentencetransformers: For those who want to run the inference with VLLM, there is a…

Open weights mit 29M parameters 2,048 tokens sentence-transformers

View model