all-MiniLM-L6-v2 vs USER-bge-m3

Specs, VRAM requirements and download trends — updated 19 October 2026.

sentence-transformers · A · Open weights
Params
20 M
Context
512
30d
177.6 M
apache-2.0 · commercial OK
deepvk · B · Open weights
Params
360 M
Context
8,192
30d
361 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification all-MiniLM-L6-v2 USER-bge-m3
Parameters 20 M 360 M
Architecture BertModel XLMRobertaModel
Context length 512 8,192
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1 1
Downloads 30d 177,602,109 361,260
Downloads all time 4.2 B 6.3 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2024-07-05

Download trend

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

259.7 M361 K
all-MiniLM-L6-v2 USER-bge-m3

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
USER-bge-m3 · fp16 2.1 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons