koelectra-small-v3-nsmc vs roberta_toxicity_classifier
Specs, VRAM requirements and download trends — updated 24 September 2026.
daekeun-ml · A · Open weights
Params
10 M
Context
512
30d
283 K
mit · 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 | koelectra-small-v3-nsmc | roberta_toxicity_classifier |
|---|---|---|
| Parameters | 10 M | — |
| Architecture | ElectraForSequenceClassification | RobertaForSequenceClassification |
| Context length | 512 | 512 |
| Licence | mit | openrail++ |
| Commercial use | Allowed | Conditional |
| Languages | 1 | 1 |
| Downloads 30d | 282,514 | 230,823 |
| Downloads all time | 13.1 M | 5.0 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.6 M222 K
koelectra-small-v3-nsmc
roberta_toxicity_classifier
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
koelectra-small-v3-nsmc · fp16
0.6 GB / 24 GB
Adjacent comparisons
bge-reranker-v2-m3 vs roberta_toxicity_classifier
finbert vs roberta_toxicity_classifier
bge-reranker-base vs roberta_toxicity_classifier
Prompt-Guard-86M vs roberta_toxicity_classifier
distilbert-base-uncased-finetuned-sst-2-english vs roberta_toxicity_classifier
twitter-roberta-base-sentiment-latest vs roberta_toxicity_classifier