Qwen3-Embedding-0.6B vs multilingual-e5-large
Specs, VRAM requirements and download trends — updated 20 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Embedding-0.6B | multilingual-e5-large |
|---|---|---|
| Parameters | 600 M | 560 M |
| Architecture | Qwen3ForCausalLM | XLMRobertaModel |
| Context length | 32,768 | 512 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | 94 |
| Downloads 30d | 8,622,694 | 7,163,955 |
| Downloads all time | 87.4 M | 109.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-06-03 | 2023-06-30 |
Download trend
Daily snapshots, last 55 days (28 Jul – 20 Sep)
10.5 M6.6 M
Qwen3-Embedding-0.6B
multilingual-e5-large
A overtook B on 7 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Embedding-0.6B · fp16
1.9 GB / 24 GB
multilingual-e5-large · fp16
3.0 GB / 24 GB