paraphrase-albert-small-v2 by Sentence Transformers

Runs On

What it takes to serve paraphrase-albert-small-v2 (12M 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-albert-small-v2

Our memory table rounds this one to 0.0 GB at 16-bit, 8-bit and 4-bit alike, and that is the hardware story. paraphrase-albert-small-v2 carries 12M parameters across 6 layers and maps sentences and paragraphs into a 768-dimensional vector space for clustering and semantic search. The cheapest setup we list, one MI300X with 192 GB at $1.85 an hour on demand, is the wrong unit of account; we would co-locate it with the retrieval stack it feeds, and the ONNX and OpenVINO artifacts exist for that.

Apache 2.0 covers commercial use, modification and redistribution provided the license and copyright notices stay attached and significant changes are stated, with an express patent grant. Read the training lineage before trusting the vectors: eight datasets, among them ms_marco, snli, multi_nli, s2orc and stackexchange_xml, shaped what it calls similar. The 512-token context caps a single passage, so longer documents get chunked.

SAVRN Research, 2026-09-18

Model Card

By Sentence Transformers, published under apache-2.0, revision 9d490b476eb5.

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-albert-small-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: AlbertModel
Context length (tokens): 512
Layers: 6
Hidden size: 768
Feed-forward size: 3,072
Attention heads: 12
Vocabulary size: 30,000
Model type: albert

Identity and Version

Repository: sentence-transformers/paraphrase-albert-small-v2
Publisher: Sentence Transformers
Task: Sentence similarity
Modality: Text
Library: sentence-transformers
Parameters: 12M parameters
Languages: tf
Revision: 9d490b476eb5291c7885bb6d4961318740493cf2
First published: 2022-03-02
Last updated: 2025-03-06

Files and Weights

28 files, 693.3 MB in total. The weights are 15 files totalling 690.6 MB in bin, h5, onnx, ot, safetensors.

Weights15 files · 690.6 MB

Configuration6 files · 1.7 KB

Tokenizer3 files · 2.1 MB

Documentation1 file · 3.8 KB

Other2 files · 622.2 KB

Repository1 file · 744 B

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	46.7 MB	1343900266ca
onnx/model.onnx	Weights	44.6 MB	af3ed44c5255
onnx/model_O1.onnx	Weights	44.5 MB	6796f59e33f3
onnx/model_O2.onnx	Weights	79.8 MB	c2061abd495d
onnx/model_O3.onnx	Weights	79.8 MB	c2061abd495d
onnx/model_O4.onnx	Weights	39.9 MB	e8abd6bd7093
onnx/model_qint8_arm64.onnx	Weights	39.8 MB	c2f2aea7f9d7
onnx/model_qint8_avx512.onnx	Weights	39.8 MB	c2f2aea7f9d7
onnx/model_qint8_avx512_vnni.onnx	Weights	39.8 MB	c2f2aea7f9d7
onnx/model_quint8_avx2.onnx	Weights	39.8 MB	d67e0a288964
openvino/openvino_model.bin	Weights	44.4 MB	c27eb1159679
openvino/openvino_model_qint8_quantized.bin	Weights	11.3 MB	663fc19fd589
pytorch_model.bin	Weights	46.7 MB	4120d577507f
rust_model.ot	Weights	46.7 MB	c24ca54a1794
tf_model.h5	Weights	46.8 MB	759fe84f34b1
1_Pooling/config.json	Configuration	190 B	—
config.json	Configuration	827 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	245 B	—
README.md	Documentation	3.8 KB	—
openvino/openvino_model.xml	Other	248.4 KB	—
openvino/openvino_model_qint8_quantized.xml	Other	373.8 KB	—
.gitattributes	Repository	744 B	—
spiece.model	Tokenizer	760.3 KB	fefb02b667a6
tokenizer.json	Tokenizer	1.3 MB	—
tokenizer_config.json	Tokenizer	465 B	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 690.6 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	690.6 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-albert-small-v2

How much GPU memory does paraphrase-albert-small-v2 need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (12M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run paraphrase-albert-small-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-albert-small-v2 commercially?

Yes. paraphrase-albert-small-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-albert-small-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

paraphrase-MiniLM-L3-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 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

bge-m3

Beijing Academy of Artificial Intelligence

For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. Some suggestions for retrieval pipeline in RAG We recommend to use the following pipeline: hybrid retrieval + re-ranking. - Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings. To…

Open weights mit 8,194 tokens sentence-transformers

View model