all-mpnet-base-v2 vs paraphrase-MiniLM-L3-v2
Specs, VRAM requirements and download trends — updated 10 November 2026.
sentence-transformers · A · Open weights
Params
110 M
Context
512
30d
20.5 M
apache-2.0 · commercial OK
sentence-transformers · B · Open weights
Params
20 M
Context
512
30d
919 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-mpnet-base-v2 | paraphrase-MiniLM-L3-v2 |
|---|---|---|
| Parameters | 110 M | 20 M |
| Architecture | MPNetForMaskedLM | BertModel |
| Context length | 512 | 512 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 20,462,590 | 919,051 |
| Downloads all time | 1.4 B | 25.5 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)
25.4 M574 K
all-mpnet-base-v2
paraphrase-MiniLM-L3-v2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
paraphrase-MiniLM-L3-v2 · fp16
0.6 GB / 24 GB
all-mpnet-base-v2 · fp16
1.0 GB / 24 GB