multilingual-e5-small vs nomic-embed-text-v1.5

Specs, VRAM requirements and download trends — updated 20 September 2026.

intfloat · A
Params
120 M
Context
512
30d
12.3 M
mit · commercial OK
nomic-ai · B
Params
140 M
Context
2,048
30d
14.7 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification multilingual-e5-small nomic-embed-text-v1.5
Parameters 120 M 140 M
Architecture BertModel NomicBertModel
Context length 512 2,048
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages 94 1
Downloads 30d 12,263,238 14,708,283
Downloads all time 114.0 M 156.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
MTEB ArguAna (reported) 19.061 57.966
MTEB AmazonPolarityClassification (reported) 88.655562950325 91.804263016433
MTEB AmazonReviewsClassification (en) (reported) 43.731873486542 46.593296422632
MTEB AmazonCounterfactualClassification (en) (reported) 67.954536791031 69.355865658579
First seen on the Hub 2023-06-30 2024-02-10

Download trend

Daily snapshots, last 55 days (28 Jul – 20 Sep)

16.6 M11.3 M
multilingual-e5-small nomic-embed-text-v1.5

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

multilingual-e5-small · fp16 1.0 GB / 24 GB
✅ Runs comfortably
nomic-embed-text-v1.5 · fp16 1.1 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons