bge-reranker-v2-m3 vs roberta_toxicity_classifier
Specs, VRAM requirements and download trends — updated 24 September 2026.
BAAI · A · Open weights
Params
570 M
Context
8,192
30d
14.8 M
apache-2.0 · commercial OK
s-nlp · B · Open weights
Params
—
Context
512
30d
231 K
openrail++ licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | bge-reranker-v2-m3 | roberta_toxicity_classifier |
|---|---|---|
| Parameters | 570 M | — |
| Architecture | XLMRobertaForSequenceClassification | RobertaForSequenceClassification |
| Context length | 8,192 | 512 |
| Licence | apache-2.0 | openrail++ |
| Commercial use | Allowed | Conditional |
| Languages | 1 | 1 |
| Downloads 30d | 14,772,977 | 230,823 |
| Downloads all time | 166.8 M | 5.0 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2024-03-15 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
18.9 M222 K
bge-reranker-v2-m3
roberta_toxicity_classifier
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
bge-reranker-v2-m3 · fp16
3.1 GB / 24 GB