bge-m3 vs nomic-embed-text-v2-moe

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

BAAI · A · Open weights
Params
—
Context
8,192
30d
29.6 M
mit · commercial OK
nomic-ai · B · Open weights
Params
480 M
Context
—
30d
736 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification bge-m3 nomic-embed-text-v2-moe
Parameters — 480 M
Architecture XLMRobertaModel NomicBertModel
Context length 8,192 —
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages — 101
Downloads 30d 29,564,329 735,530
Downloads all time 362.4 M 17.9 M
Quantizations on the Hub — SAFETENSORS
Gated No No
First seen on the Hub 2024-01-27 2025-02-07

Download trend

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

38.2 M736 K
bge-m3 nomic-embed-text-v2-moe

VRAM side by side

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

nomic-embed-text-v2-moe · fp16 2.7 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons