Deepset Mxbai Embed De Large v1 vs Mxbai Embed Large v1
Deepset Mxbai Embed De Large v1—
Mxbai Embed Large v145.9
| Benchmark | Deepset Mxbai Embed De Large v1 | Mxbai Embed Large v1 |
|---|---|---|
| MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) | — | 45.9 |
Specs
| Spec | Deepset Mxbai Embed De Large v1 | Mxbai Embed Large v1 |
|---|---|---|
| Context | 1K | 1K |
| Weights | Open | Open |
| Released | Jul 2024 | Mar 2024 |
| Dimensions | 1,024 | 1,024 |
| Max input | 1K tokens | 1K tokens |
| Languages | en, de | en |
| Memory (4-bit) | 0.3 GB | 0.2 GB |
| Licence | Apache-2.0 | Apache-2.0 |
| Commercial use | Allowed | Allowed |
What breaks when you switch
Deepset Mxbai Embed De Large v1 → Mxbai Embed Large v1
Re-embed your whole corpus›
Vectors from different models can't be mixed.
Languages: loses de
Mxbai Embed Large v1 → Deepset Mxbai Embed De Large v1
Re-embed your whole corpus›
Vectors from different models can't be mixed.