bge-reranker-v2-m3 vs Prompt-Guard-86M
Specs, VRAM requirements and download trends — updated 10 November 2026.
BAAI · A · Open weights
Params
570 M
Context
8,192
30d
14.8 M
apache-2.0 · commercial OK
meta-llama · B · Open weights
Params
280 M
Context
—
30d
1.7 M
llama3.1 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | bge-reranker-v2-m3 | Prompt-Guard-86M |
|---|---|---|
| Parameters | 570 M | 280 M |
| Architecture | XLMRobertaForSequenceClassification | DebertaV2ForSequenceClassification |
| Context length | 8,192 | — |
| Licence | apache-2.0 | llama3.1 |
| Commercial use | Allowed | Conditional |
| Languages | 1 | 1 |
| Downloads 30d | 14,772,977 | 1,692,077 |
| Downloads all time | 166.8 M | 21.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2024-03-15 | 2024-07-21 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
18.9 M1.7 M
bge-reranker-v2-m3
Prompt-Guard-86M
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Prompt-Guard-86M · fp16
1.8 GB / 24 GB
bge-reranker-v2-m3 · fp16
3.1 GB / 24 GB
Adjacent comparisons
bge-reranker-v2-m3 vs twitter-roberta-base-sentiment-latest
bge-reranker-v2-m3 vs Bangla-twoclass-Sentiment-Analyzer
bge-reranker-v2-m3 vs bge-reranker-base
bge-reranker-v2-m3 vs roberta-base-go_emotions
bge-reranker-v2-m3 vs fasttext-language-identification
bge-reranker-v2-m3 vs ms-marco-MiniLM-L-6-v2