all-MiniLM-L6-v2 vs Qwen3-VL-Embedding-2B

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

sentence-transformers · A
Params
20 M
Context
512
30d
257.8 M
apache-2.0 · 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 all-MiniLM-L6-v2 Qwen3-VL-Embedding-2B
Parameters 20 M 2.1 B
Architecture BertModel Qwen3VLForConditionalGeneration
Context length 512
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 257,806,986 1,350,626
Downloads all time 3.5 B 8.9 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2022-03-02 2026-01-07

Download trend

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

259.6 M1.3 M
all-MiniLM-L6-v2 Qwen3-VL-Embedding-2B

VRAM side by side

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

all-MiniLM-L6-v2 · fp16 0.6 GB / 24 GB
✅ Runs comfortably
Qwen3-VL-Embedding-2B · fp16 5.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons