all-mpnet-base-v2 vs multilingual-e5-small
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
intfloat · B · Open weights
Params
120 M
Context
512
30d
9.4 M
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-mpnet-base-v2 | multilingual-e5-small |
|---|---|---|
| Parameters | 110 M | 120 M |
| Architecture | MPNetForMaskedLM | BertModel |
| Context length | 512 | 512 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 94 |
| Downloads 30d | 20,462,590 | 9,411,746 |
| Downloads all time | 1.4 B | 130.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2023-06-30 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
25.4 M9.2 M
all-mpnet-base-v2
multilingual-e5-small
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
all-mpnet-base-v2 · fp16
1.0 GB / 24 GB
multilingual-e5-small · fp16
1.0 GB / 24 GB