all-MiniLM-L6-v2 vs bge-m3-spa-law-qa

Specs, VRAM requirements and download trends — updated 6 August 2026.

sentence-transformers · A
Params
20 M
Context
512
30d
257.8 M
apache-2.0 · commercial OK
littlejohn-ai · B
Params
570 M
Context
30d
473 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification all-MiniLM-L6-v2 bge-m3-spa-law-qa
Parameters 20 M 570 M
Architecture BertModel XLMRobertaModel
Context length 512
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1 1
Downloads 30d 257,806,986 473,107
Downloads all time 3.5 B 3.5 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No Yes — accept licence
First seen on the Hub 2022-03-02 2024-07-22

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

259.6 M473 K
all-MiniLM-L6-v2 bge-m3-spa-law-qa

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
bge-m3-spa-law-qa · fp16 3.1 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons