all-MiniLM-L6-v2 vs paraphrase-MiniLM-L12-v2
Specs, VRAM requirements and download trends — updated 6 August 2026.
sentence-transformers · A
Params
20 M
Context
512
30d
257.8 M
apache-2.0 · commercial OK
sentence-transformers · B
Params
30 M
Context
512
30d
454 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-MiniLM-L6-v2 | paraphrase-MiniLM-L12-v2 |
|---|---|---|
| Parameters | 20 M | 30 M |
| Architecture | BertModel | BertModel |
| Context length | 512 | 512 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 257,806,986 | 454,000 |
| Downloads all time | 3.5 B | 7.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2022-03-02 |
Download trend
10 days of snapshots recorded — the trend chart unlocks at 7 days.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
all-MiniLM-L6-v2 · fp16
0.6 GB / 24 GB
paraphrase-MiniLM-L12-v2 · fp16
0.7 GB / 24 GB