all-MiniLM-L6-v2 vs bm25

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

sentence-transformers · A · Open weights
Params
20 M
Context
512
30d
177.6 M
apache-2.0 · commercial OK
Qdrant · B · Open weights
Params
—
Context
—
30d
905 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification all-MiniLM-L6-v2 bm25
Parameters 20 M —
Architecture BertModel —
Context length 512 —
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1 18
Downloads 30d 177,602,109 904,577
Downloads all time 4.2 B 10.8 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2022-03-02 2024-06-13

Download trend

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

259.7 M900 K
all-MiniLM-L6-v2 bm25

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

Adjacent comparisons