granite-embedding-small-english-r2 vs dragon-multiturn-context-encoder

Specs, VRAM requirements and download trends — updated 21 September 2026.

ibm-granite · A
Params
50 M
Context
8,192
30d
6.3 M
apache-2.0 · commercial OK
nvidia · B
Params
Context
512
30d
749 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification granite-embedding-small-english-r2 dragon-multiturn-context-encoder
Parameters 50 M
Architecture ModernBertModel BertModel
Context length 8,192 512
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages 1 1
Downloads 30d 6,277,600 748,659
Downloads all time 24.3 M 6.1 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2025-07-17 2024-04-30

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

6.4 M447 K
granite-embedding-small-english-r2 dragon-multiturn-context-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

Adjacent comparisons