paraphrase-multilingual-MiniLM-L12-v2 vs KR-SBERT-V40K-klueNLI-augSTS

Specs, VRAM requirements and download trends — updated 10 November 2026.

sentence-transformers · A · Open weights
Params
120 M
Context
512
30d
27.1 M
apache-2.0 · commercial OK
snunlp · B · Open weights
Params
—
Context
512
30d
467 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification paraphrase-multilingual-MiniLM-L12-v2 KR-SBERT-V40K-klueNLI-augSTS
Parameters 120 M —
Architecture BertModel BertModel
Context length 512 512
Licence apache-2.0 —
Commercial use Allowed Unknown
Languages 50 1
Downloads 30d 27,107,729 466,660
Downloads all time 671.8 M 7.9 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2022-03-02 2022-05-03

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

57.1 M467 K
paraphrase-multilingual-MiniLM-L12-v2 KR-SBERT-V40K-klueNLI-augSTS

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

paraphrase-multilingual-MiniLM-L12-v2 · fp16 1.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons