Prompt-Guard-86M vs toxic-comment-model
Specs, VRAM requirements and download trends — updated 21 September 2026.
meta-llama · A · Open weights
Params
280 M
Context
—
30d
1.7 M
llama3.1 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Prompt-Guard-86M | toxic-comment-model |
|---|---|---|
| Parameters | 280 M | — |
| Architecture | DebertaV2ForSequenceClassification | DistilBertForSequenceClassification |
| Context length | — | 512 |
| Licence | llama3.1 | — |
| Commercial use | Conditional | Unknown |
| Languages | 1 | 1 |
| Downloads 30d | 1,692,077 | 224,999 |
| Downloads all time | 21.5 M | 22.4 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-21 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.6 M225 K
Prompt-Guard-86M
toxic-comment-model
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Prompt-Guard-86M · fp16
1.8 GB / 24 GB