all-MiniLM-L6-v2 vs paraphrase-multilingual-MiniLM-L12-v2

Specs, VRAM requirements and download trends — updated 20 September 2026.

sentence-transformers · A
Params
20 M
Context
512
30d
254.1 M
apache-2.0 · commercial OK
sentence-transformers · B
Params
120 M
Context
512
30d
45.9 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification all-MiniLM-L6-v2 paraphrase-multilingual-MiniLM-L12-v2
Parameters 20 M 120 M
Architecture BertModel BertModel
Context length 512 512
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1 50
Downloads 30d 254,149,235 45,855,533
Downloads all time 3.9 B 607.2 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 55 days (28 Jul – 20 Sep)

259.7 M45.3 M
all-MiniLM-L6-v2 paraphrase-multilingual-MiniLM-L12-v2

VRAM side by side

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

all-MiniLM-L6-v2 · fp16 0.6 GB / 24 GB
✅ Runs comfortably
paraphrase-multilingual-MiniLM-L12-v2 · fp16 1.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons