all-mpnet-base-v2 vs all-roberta-large-v1
Specs, VRAM requirements and download trends — updated 21 September 2026.
sentence-transformers · A
Params
110 M
Context
512
30d
22.2 M
apache-2.0 · commercial OK
sentence-transformers · B
Params
360 M
Context
512
30d
632 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-mpnet-base-v2 | all-roberta-large-v1 |
|---|---|---|
| Parameters | 110 M | 360 M |
| Architecture | MPNetForMaskedLM | RobertaForMaskedLM |
| Context length | 512 | 512 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 22,242,121 | 631,850 |
| Downloads all time | 1.3 B | 26.7 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 56 days (28 Jul – 21 Sep)
28.0 M632 K
all-mpnet-base-v2
all-roberta-large-v1
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
all-mpnet-base-v2 · fp16
1.0 GB / 24 GB
all-roberta-large-v1 · fp16
2.1 GB / 24 GB