Qwen3-Embedding-4B vs bge-multilingual-gemma2
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Embedding-4B | bge-multilingual-gemma2 |
|---|---|---|
| Parameters | 4.0 B | 9.2 B |
| Architecture | Qwen3ForCausalLM | Gemma2Model |
| Context length | 40,960 | 8,192 |
| Licence | apache-2.0 | gemma |
| Commercial use | Allowed | Conditional |
| Languages | — | — |
| Downloads 30d | 3,366,938 | 1,130,043 |
| Downloads all time | 16.5 M | 11.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-06-03 | 2024-07-25 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
3.4 M1.1 M
Qwen3-Embedding-4B
bge-multilingual-gemma2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Embedding-4B · fp16
10.0 GB / 24 GB
bge-multilingual-gemma2 · fp16
42.5 GB / 24 GB