paraphrase-MiniLM-L3-v2 vs multi-qa-MiniLM-L6-cos-v1
Specs, VRAM requirements and download trends — updated 6 August 2026.
sentence-transformers · A
Params
20 M
Context
512
30d
2.6 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | paraphrase-MiniLM-L3-v2 | multi-qa-MiniLM-L6-cos-v1 |
|---|---|---|
| Parameters | 20 M | 20 M |
| Architecture | BertModel | BertModel |
| Context length | 512 | 512 |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 2,608,179 | 881,970 |
| Downloads all time | 22.5 M | 110.1 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 10 days (28 Jul – 6 Aug)
2.6 M826 K
paraphrase-MiniLM-L3-v2
multi-qa-MiniLM-L6-cos-v1
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
paraphrase-MiniLM-L3-v2 · fp16
0.6 GB / 24 GB
multi-qa-MiniLM-L6-cos-v1 · fp16
0.6 GB / 24 GB