intfloat / sentence-similarity updated 4 months ago

multilingual-e5-small

Name: multilingual-e5-small
Author: intfloat

Multilingual E5 Text Embeddings: A Technical Report. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024

Params

120 M

Context

512

Downloads 30d

15.6 M

Likes

380

Commercial use: allowed mit Not gated SAFETENSORS 94 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

15.8 M15.4 M

Jul 28Jul 31Aug 3Aug 6

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	0.5 GB	1.0 GB	✅ Runs comfortably

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

Architecture: BertModel
Parameters: 120 M
Tensor type: F32
Context length: 512
Vocabulary: 250,037
Layers / heads: 12 / 12
Licence: mit
First seen on the Hub: 2023-06-30
Training datasets: undisclosed
MTEB ArguAna (reported): 19.061
MTEB AmazonPolarityClassification (reported): 88.655562950325
MTEB AmazonReviewsClassification (de) (reported): 39.386353063768
MTEB AmazonReviewsClassification (en) (reported): 43.731873486542
MTEB AmazonReviewsClassification (es) (reported): 39.301223469483
MTEB AmazonReviewsClassification (fr) (reported): 37.97974261868
MTEB AmazonReviewsClassification (ja) (reported): 37.073993697683
MTEB AmazonReviewsClassification (zh) (reported): 36.623172738743
MTEB AmazonCounterfactualClassification (de) (reported): 69.879634216067
MTEB AmazonCounterfactualClassification (en) (reported): 67.954536791031
MTEB AmazonCounterfactualClassification (ja) (reported): 52.07153895475
MTEB AmazonCounterfactualClassification (en-ext) (reported): 63.001084800376
Added to our catalog: 2026-07-28

Compare with

Appears in

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