finbert vs roberta-base-openai-detector
Specs, VRAM requirements and download trends — updated 24 October 2026.
ProsusAI · A · Open weights
Params
110 M
Context
512
30d
3.9 M
cc-by-nc-sa-4.0 · non-commercial
openai-community · B · Open weights
Params
125 M
Context
512
30d
381 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | finbert | roberta-base-openai-detector |
|---|---|---|
| Parameters | 110 M | 125 M |
| Architecture | BertForSequenceClassification | RobertaForSequenceClassification |
| Context length | 512 | 512 |
| Licence | cc-by-nc-sa-4.0 | mit |
| Commercial use | Not allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 3,916,849 | 380,744 |
| Downloads all time | 125.1 M | 9.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2022-03-02 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
6.5 M223 K
finbert
roberta-base-openai-detector
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
finbert · fp16
1.0 GB / 24 GB
roberta-base-openai-detector · fp16
1.1 GB / 24 GB