multilingual-e5-large vs jina-embeddings-v3

Specs, VRAM requirements and download trends — updated 6 August 2026.

intfloat · A
Params
560 M
Context
512
30d
7.5 M
mit · commercial OK
jinaai · B
Params
570 M
Context
8,192
30d
3.2 M
cc-by-nc-4.0 · non-commercial

Specification comparison

Differences are highlighted; identical values are muted.

Specification multilingual-e5-large jina-embeddings-v3
Parameters 560 M 570 M
Architecture XLMRobertaModel XLMRobertaModel
Context length 512 8,192
Licence mit cc-by-nc-4.0
Commercial use Allowed Not allowed
Languages 94 94
Downloads 30d 7,485,047 3,241,662
Downloads all time 97.6 M 77.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2023-06-30 2024-09-05

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

8.3 M3.2 M
multilingual-e5-large jina-embeddings-v3

VRAM side by side

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

jina-embeddings-v3 · fp16 1.8 GB / 24 GB
✅ Runs comfortably
multilingual-e5-large · fp16 3.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons