Qwen3-Embedding-4B vs all-MiniLM-L6-v2

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

Qwen · A
Params
4.0 B
Context
40,960
30d
3.4 M
apache-2.0 · commercial OK
Xenova · B
Params
Context
512
30d
2.9 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-Embedding-4B all-MiniLM-L6-v2
Parameters 4.0 B
Architecture Qwen3ForCausalLM BertModel
Context length 40,960 512
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 3,366,938 2,885,743
Downloads all time 16.5 M 23.6 M
Quantizations on the Hub SAFETENSORS
Gated No No
First seen on the Hub 2025-06-03 2023-05-02

Download trend

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

3.4 M2.8 M
Qwen3-Embedding-4B all-MiniLM-L6-v2 A overtook B on 31 Jul

VRAM side by side

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

Qwen3-Embedding-4B · fp16 10.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons