multilingual-e5-large vs llama-nemotron-embed-1b-v2

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

intfloat · A
Params
560 M
Context
512
30d
7.2 M
mit · commercial OK
nvidia · B
Params
1.2 B
Context
131,072
30d
425 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification multilingual-e5-large llama-nemotron-embed-1b-v2
Parameters 560 M 1.2 B
Architecture XLMRobertaModel LlamaBidirectionalModel
Context length 512 131,072
Licence mit other
Commercial use Allowed Unknown
Languages 94 1
Downloads 30d 7,173,073 425,488
Downloads all time 109.3 M 4.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2023-06-30 2025-10-16

Download trend

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

8.3 M425 K
multilingual-e5-large llama-nemotron-embed-1b-v2

VRAM side by side

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

multilingual-e5-large · fp16 3.0 GB / 24 GB
✅ Runs comfortably
llama-nemotron-embed-1b-v2 · fp16 @ 128K ctx 6.2 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons