finbert vs bge-reranker-base

Specs, VRAM requirements and download trends — updated 10 November 2026.

ProsusAI · A · Open weights
Params
110 M
Context
512
30d
3.3 M
cc-by-nc-sa-4.0 · non-commercial
BAAI · B · Open weights
Params
280 M
Context
512
30d
2.4 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification finbert bge-reranker-base
Parameters 110 M 280 M
Architecture BertForSequenceClassification XLMRobertaForSequenceClassification
Context length 512 512
Licence cc-by-nc-sa-4.0 mit
Commercial use Not allowed Allowed
Languages 1 2
Downloads 30d 3,256,194 2,364,917
Downloads all time 127.0 M 54.6 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2023-09-11

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

5.5 M2.4 M
finbert bge-reranker-base

VRAM side by side

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

finbert · fp16 1.0 GB / 24 GB
✅ Runs comfortably
bge-reranker-base · fp16 1.8 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons