Prompt-Guard-86M vs twitter-roberta-base-sentiment-latest

Specs, VRAM requirements and download trends — updated 10 November 2026.

meta-llama · A · Open weights
Params
280 M
Context
—
30d
1.7 M
llama3.1 licence · conditional
cardiffnlp · B · Open weights
Params
—
Context
512
30d
2.4 M
cc-by-4.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Prompt-Guard-86M twitter-roberta-base-sentiment-latest
Parameters 280 M —
Architecture DebertaV2ForSequenceClassification RobertaForSequenceClassification
Context length — 512
Licence llama3.1 cc-by-4.0
Commercial use Conditional Allowed
Languages 1 1
Downloads 30d 1,692,077 2,413,051
Downloads all time 21.5 M 332.1 M
Quantizations on the Hub SAFETENSORS —
Gated Yes — accept licence No
First seen on the Hub 2024-07-21 2022-03-15

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

4.6 M1.7 M
Prompt-Guard-86M twitter-roberta-base-sentiment-latest

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Prompt-Guard-86M · fp16 1.8 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons