all-MiniLM-L6-v2 vs MedCPT-Query-Encoder

Specs, VRAM requirements and download trends — updated 5 August 2026.

Xenova · A
Params
Context
512
30d
2.8 M
apache-2.0 · commercial OK
ncbi · B
Params
110 M
Context
512
30d
454 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification all-MiniLM-L6-v2 MedCPT-Query-Encoder
Parameters 110 M
Architecture BertModel BertModel
Context length 512 512
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages
Downloads 30d 2,792,069 453,977
Downloads all time 23.6 M 4.2 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2023-05-02 2023-10-24

Download trend

Daily snapshots, last 11 days (28 Jul – 7 Aug)

2.9 M454 K
all-MiniLM-L6-v2 MedCPT-Query-Encoder

VRAM side by side

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

MedCPT-Query-Encoder · fp16 1.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons