Prompt-Guard-86M vs roberta-large-mnli
Specs, VRAM requirements and download trends — updated 24 October 2026.
meta-llama · A · Open weights
Params
280 M
Context
—
30d
2.4 M
llama3.1 licence · conditional
FacebookAI · B · Open weights
Params
360 M
Context
512
30d
246 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Prompt-Guard-86M | roberta-large-mnli |
|---|---|---|
| Parameters | 280 M | 360 M |
| Architecture | DebertaV2ForSequenceClassification | RobertaForSequenceClassification |
| Context length | — | 512 |
| Licence | llama3.1 | mit |
| Commercial use | Conditional | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 2,376,548 | 245,953 |
| Downloads all time | 20.8 M | 25.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-21 | 2022-03-02 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
4.6 M203 K
Prompt-Guard-86M
roberta-large-mnli
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Prompt-Guard-86M · fp16
1.8 GB / 24 GB
roberta-large-mnli · fp16
2.1 GB / 24 GB