bge-m3 vs Qwen3-VL-Embedding-2B

Specs, VRAM requirements and download trends — updated 6 August 2026.

BAAI · A
Params
Context
8,192
30d
35.0 M
mit · commercial OK
Qwen · B
Params
2.1 B
Context
30d
1.4 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification bge-m3 Qwen3-VL-Embedding-2B
Parameters 2.1 B
Architecture XLMRobertaModel Qwen3VLForConditionalGeneration
Context length 8,192
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 34,991,851 1,350,626
Downloads all time 250.3 M 8.9 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2024-01-27 2026-01-07

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

35.5 M1.3 M
bge-m3 Qwen3-VL-Embedding-2B

VRAM side by side

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

Qwen3-VL-Embedding-2B · fp16 5.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons