Qwen3-VL-Embedding-8B vs all-MiniLM-L6-v2-onnx
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · A · Open weights
Params
8.1 B
Context
—
30d
690 K
apache-2.0 · commercial OK
Qdrant · B · Open weights
Params
—
Context
512
30d
1.6 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-VL-Embedding-8B | all-MiniLM-L6-v2-onnx |
|---|---|---|
| Parameters | 8.1 B | — |
| Architecture | Qwen3VLForConditionalGeneration | BertModel |
| Context length | — | 512 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 690,297 | 1,601,209 |
| Downloads all time | 12.0 M | 12.7 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2026-01-07 | 2024-01-16 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.0 M690 K
Qwen3-VL-Embedding-8B
all-MiniLM-L6-v2-onnx
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-VL-Embedding-8B · fp16
19.6 GB / 24 GB