bge-m3 vs Qwen3-VL-Embedding-8B
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | bge-m3 | Qwen3-VL-Embedding-8B |
|---|---|---|
| Parameters | — | 8.1 B |
| Architecture | XLMRobertaModel | Qwen3VLForConditionalGeneration |
| Context length | 8,192 | — |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 37,633,121 | 1,170,273 |
| Downloads all time | 310.2 M | 10.2 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 56 days (28 Jul – 21 Sep)
38.2 M1.1 M
bge-m3
Qwen3-VL-Embedding-8B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-VL-Embedding-8B · fp16
19.6 GB / 24 GB