all-MiniLM-L12-v2 vs paraphrase-albert-small-v2
Specs, VRAM requirements and download trends — updated 21 September 2026.
sentence-transformers · A
Params
30 M
Context
512
30d
4.2 M
apache-2.0 · commercial OK
sentence-transformers · B
Params
10 M
Context
512
30d
551 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-MiniLM-L12-v2 | paraphrase-albert-small-v2 |
|---|---|---|
| Parameters | 30 M | 10 M |
| Architecture | BertModel | AlbertModel |
| Context length | 512 | 512 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 4,196,036 | 551,200 |
| Downloads all time | 253.7 M | 9.0 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)
4.2 M498 K
all-MiniLM-L12-v2
paraphrase-albert-small-v2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
paraphrase-albert-small-v2 · fp16
0.6 GB / 24 GB
all-MiniLM-L12-v2 · fp16
0.7 GB / 24 GB