bge-reranker-large vs embeddinggemma-2-ONNX

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

BAAI · A · Open weights
Params
560 M
Context
512
30d
2.0 M
mit · commercial OK
onnx-community · B · Open weights
Params
744 M
Context
—
30d
531 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification bge-reranker-large embeddinggemma-2-ONNX
Parameters 560 M 744 M
Architecture XLMRobertaForSequenceClassification EmbeddingGemma2Model
Context length 512 —
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages 2 1
Downloads 30d 2,041,111 530,928
Downloads all time 38.3 M 623 K
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2023-09-12 2026-10-04

Download trend

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

2.8 M367 K
bge-reranker-large embeddinggemma-2-ONNX

VRAM side by side

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

bge-reranker-large · fp16 3.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons