paraphrase-multilingual-mpnet-base-v2 vs all-roberta-large-v1
Specs, VRAM requirements and download trends — updated 10 November 2026.
sentence-transformers · A · Open weights
Params
280 M
Context
512
30d
9.1 M
apache-2.0 · commercial OK
sentence-transformers · B · Open weights
Params
360 M
Context
512
30d
612 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | paraphrase-multilingual-mpnet-base-v2 | all-roberta-large-v1 |
|---|---|---|
| Parameters | 280 M | 360 M |
| Architecture | XLMRobertaModel | RobertaForMaskedLM |
| Context length | 512 | 512 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 50 | 1 |
| Downloads 30d | 9,113,974 | 612,115 |
| Downloads all time | 149.4 M | 27.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
11.1 M564 K
paraphrase-multilingual-mpnet-base-v2
all-roberta-large-v1
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
paraphrase-multilingual-mpnet-base-v2 · fp16
1.8 GB / 24 GB
all-roberta-large-v1 · fp16
2.1 GB / 24 GB
Adjacent comparisons
bge-m3 vs paraphrase-multilingual-mpnet-base-v2
all-MiniLM-L6-v2 vs paraphrase-multilingual-mpnet-base-v2
paraphrase-multilingual-MiniLM-L12-v2 vs paraphrase-multilingual-mpnet-base-v2
all-mpnet-base-v2 vs paraphrase-multilingual-mpnet-base-v2
nomic-embed-text-v1.5 vs paraphrase-multilingual-mpnet-base-v2
paraphrase-multilingual-mpnet-base-v2 vs multilingual-e5-base