multi-qa-MiniLM-L6-cos-v1 vs bge-small-en-v1.5-onnx-Q

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

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

Specification comparison

Differences are highlighted; identical values are muted.

Specification multi-qa-MiniLM-L6-cos-v1 bge-small-en-v1.5-onnx-Q
Parameters 20 M —
Architecture BertModel BertModel
Context length 512 512
Licence — mit
Commercial use Unknown Allowed
Languages 1 —
Downloads 30d 661,289 1,964,421
Downloads all time 112.5 M 13.4 M
Quantizations on the Hub SAFETENSORS —
Gated No No
First seen on the Hub 2022-03-02 2024-01-15

Download trend

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

2.0 M599 K
multi-qa-MiniLM-L6-cos-v1 bge-small-en-v1.5-onnx-Q

VRAM side by side

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

multi-qa-MiniLM-L6-cos-v1 · fp16 0.6 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons