multilingual-e5-large vs dragon-multiturn-query-encoder
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | multilingual-e5-large | dragon-multiturn-query-encoder |
|---|---|---|
| Parameters | 560 M | — |
| Architecture | XLMRobertaModel | BertModel |
| Context length | 512 | 512 |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | 94 | 1 |
| Downloads 30d | 7,173,073 | 750,094 |
| Downloads all time | 109.3 M | 6.0 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2023-06-30 | 2024-04-30 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
8.3 M449 K
multilingual-e5-large
dragon-multiturn-query-encoder
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
multilingual-e5-large · fp16
3.0 GB / 24 GB