multilingual-e5-large-instruct vs bge-reranker-large

Specs, VRAM requirements and download trends — updated 21 September 2026.

intfloat · A
Params
560 M
Context
512
30d
1.6 M
mit · commercial OK
BAAI · B
Params
560 M
Context
512
30d
2.8 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification multilingual-e5-large-instruct bge-reranker-large
Parameters 560 M 560 M
Architecture XLMRobertaModel XLMRobertaForSequenceClassification
Context length 512 512
Licence mit mit
Commercial use Allowed Allowed
Languages 94 2
Downloads 30d 1,575,893 2,815,668
Downloads all time 32.9 M 34.8 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-02-08 2023-09-12

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

2.8 M1.6 M
multilingual-e5-large-instruct bge-reranker-large

VRAM side by side

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

multilingual-e5-large-instruct · fp16 1.8 GB / 24 GB
✅ Runs comfortably
bge-reranker-large · fp16 3.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons