all-MiniLM-L12-v2 vs gte-small

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

sentence-transformers · A · Open weights
Params
30 M
Context
512
30d
2.5 M
apache-2.0 · commercial OK
thenlper · B · Open weights
Params
30 M
Context
512
30d
2.3 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification all-MiniLM-L12-v2 gte-small
Parameters 30 M 30 M
Architecture BertModel BertModel
Context length 512 512
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 1 1
Downloads 30d 2,479,152 2,343,089
Downloads all time 258.2 M 34.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2023-07-27

Download trend

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

4.2 M837 K
all-MiniLM-L12-v2 gte-small

VRAM side by side

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

gte-small · fp16 0.6 GB / 24 GB
✅ Runs comfortably
all-MiniLM-L12-v2 · fp16 0.7 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons