intfloat / sentence-similarity updated 1 year ago

e5-small-v2

Name: e5-small-v2
Author: intfloat

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

Params

30 M

Context

512

Downloads 30d

739 K

Likes

121

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

760 K720 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.1 GB	0.7 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: BertModel
Parameters: 30 M
Tensor type: F32
Context length: 512
Vocabulary: 30,522
Layers / heads: 12 / 12
Licence: mit
First seen on the Hub: 2023-05-19
Training datasets: undisclosed
MTEB ArguAna (reported): 51.991
MTEB BIOSSES (reported): 78.293952655523
MTEB ArxivClusteringP2P (reported): 42.116951744707
MTEB ArxivClusteringS2S (reported): 34.795537201071
MTEB BiorxivClusteringP2P (reported): 35.885411371376
MTEB BiorxivClusteringS2S (reported): 30.052056852744
MTEB AskUbuntuDupQuestions (reported): 71.564107637515
MTEB Banking77Classification (reported): 81.55779952377
MTEB CQADupstackAndroidRetrieval (reported): 30.294
MTEB AmazonPolarityClassification (reported): 91.242975214257
MTEB AmazonReviewsClassification (en) (reported): 45.080588703812
MTEB AmazonCounterfactualClassification (en) (reported): 71.864659463986
Added to our catalog: 2026-07-28

Compare with

all-MiniLM-L6-v2 257.8 M paraphrase-multilingual-MiniLM-L12-v2 59.4 M bge-m3 35.0 M all-mpnet-base-v2 25.2 M multilingual-e5-small 15.6 M all-MiniLM-L12-v2 3.5 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB