granite-embedding-small-english-r2 vs MedCPT-Query-Encoder

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

ibm-granite · A · Open weights
Params
50 M
Context
8,192
30d
6.9 M
apache-2.0 · commercial OK
ncbi · B · Open weights
Params
110 M
Context
512
30d
454 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification granite-embedding-small-english-r2 MedCPT-Query-Encoder
Parameters 50 M 110 M
Architecture ModernBertModel BertModel
Context length 8,192 512
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages 1 —
Downloads 30d 6,856,446 453,977
Downloads all time 34.9 M 4.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-07-17 2023-10-24

Download trend

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

6.9 M454 K
granite-embedding-small-english-r2 MedCPT-Query-Encoder

VRAM side by side

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

granite-embedding-small-english-r2 · fp16 0.6 GB / 24 GB
✅ Runs comfortably
MedCPT-Query-Encoder · fp16 1.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons