bge-reranker-v2-m3 vs distilbert-multilingual-toxicity-classifier-ONNX
Specs, VRAM requirements and download trends — updated 24 October 2026.
BAAI · A · Open weights
Params
570 M
Context
8,192
30d
14.7 M
apache-2.0 · commercial OK
onnx-community · B · Open weights
Params
—
Context
512
30d
224 K
openrail++ licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | bge-reranker-v2-m3 | distilbert-multilingual-toxicity-classifier-ONNX |
|---|---|---|
| Parameters | 570 M | — |
| Architecture | XLMRobertaForSequenceClassification | DistilBertForSequenceClassification |
| Context length | 8,192 | 512 |
| Licence | apache-2.0 | openrail++ |
| Commercial use | Allowed | Conditional |
| Languages | 1 | 14 |
| Downloads 30d | 14,678,539 | 223,950 |
| Downloads all time | 157.5 M | 225 K |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2024-03-15 | 2026-02-21 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
19.3 M208 K
bge-reranker-v2-m3
distilbert-multilingual-toxicity-classifier-ONNX
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
bge-reranker-v2-m3 · fp16
3.1 GB / 24 GB