twitter-roberta-base-sentiment-latest vs prokbert-mini-promoter
Specs, VRAM requirements and download trends — updated 21 September 2026.
cardiffnlp · A
Params
—
Context
512
30d
3.1 M
cc-by-4.0 · commercial OK
neuralbioinfo · B
Params
20 M
Context
1,024
30d
302 K
cc-by-nc-4.0 · non-commercial
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | twitter-roberta-base-sentiment-latest | prokbert-mini-promoter |
|---|---|---|
| Parameters | — | 20 M |
| Architecture | RobertaForSequenceClassification | ProkBertForSequenceClassification |
| Context length | 512 | 1,024 |
| Licence | cc-by-4.0 | cc-by-nc-4.0 |
| Commercial use | Allowed | Not allowed |
| Languages | 1 | — |
| Downloads 30d | 3,134,269 | 302,206 |
| Downloads all time | 328.0 M | 637 K |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-15 | 2024-01-31 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
3.3 M302 K
twitter-roberta-base-sentiment-latest
prokbert-mini-promoter
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
prokbert-mini-promoter · fp16
0.6 GB / 24 GB
Adjacent comparisons
bge-reranker-v2-m3 vs twitter-roberta-base-sentiment-latest
finbert vs twitter-roberta-base-sentiment-latest
Prompt-Guard-86M vs twitter-roberta-base-sentiment-latest
bge-reranker-base vs twitter-roberta-base-sentiment-latest
distilbert-base-uncased-finetuned-sst-2-english vs twitter-roberta-base-sentiment-latest
koelectra-small-v3-nsmc vs twitter-roberta-base-sentiment-latest