twitter-roberta-base-sentiment-latest vs GEV-26B-Decide
Specs, VRAM requirements and download trends — updated 24 October 2026.
cardiffnlp · A · Open weights
Params
—
Context
512
30d
2.4 M
cc-by-4.0 · commercial OK
autotrust · B · Open weights
Params
25.8 B
Context
—
30d
1.2 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | twitter-roberta-base-sentiment-latest | GEV-26B-Decide |
|---|---|---|
| Parameters | — | 25.8 B |
| Architecture | RobertaForSequenceClassification | Gemma4ForConditionalGeneration |
| Context length | 512 | — |
| Licence | cc-by-4.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 2,357,197 | 1,164,579 |
| Downloads all time | 330.7 M | 1.2 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-15 | 2026-10-02 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
3.3 M310 K
twitter-roberta-base-sentiment-latest
GEV-26B-Decide
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GEV-26B-Decide · fp16
61.4 GB / 24 GB
Adjacent comparisons
bge-reranker-v2-m3 vs twitter-roberta-base-sentiment-latest
twitter-roberta-base-sentiment-latest vs roberta-base-go_emotions
finbert 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
Prompt-Guard-86M vs twitter-roberta-base-sentiment-latest