all-MiniLM-L6-v2 vs sentence-bert-base-ja-mean-tokens-v2
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-MiniLM-L6-v2 | sentence-bert-base-ja-mean-tokens-v2 |
|---|---|---|
| Parameters | — | 110 M |
| Architecture | BertModel | BertModel |
| Context length | 512 | 512 |
| Licence | apache-2.0 | cc-by-sa-4.0 |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 2,885,743 | 575,172 |
| Downloads all time | 23.6 M | 10.0 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-05-02 | 2022-03-02 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
2.9 M554 K
all-MiniLM-L6-v2
sentence-bert-base-ja-mean-tokens-v2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
sentence-bert-base-ja-mean-tokens-v2 · fp16
1.0 GB / 24 GB