Snowflake Arctic Embed L v2.0 vs Snowflake Arctic Embed M v2.0
Snowflake Arctic Embed L v2.057
Snowflake Arctic Embed M v2.0—
| Benchmark | Snowflake Arctic Embed L v2.0 | Snowflake Arctic Embed M v2.0 |
|---|---|---|
| MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages) | 57 | — |
Specs
| Spec | Snowflake Arctic Embed L v2.0 | Snowflake Arctic Embed M v2.0 |
|---|---|---|
| Context | 8K | 8K |
| Weights | Open | Open |
| Released | Dec 2024 | Dec 2024 |
| Dimensions | 1,024 | 768 |
| Max input | 8K tokens | 8K tokens |
| Languages | en, es, Estonian +68 | en, es, Estonian +68 |
| 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
Snowflake Arctic Embed L v2.0 → Snowflake Arctic Embed M v2.0
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 1,024 to 768.
Snowflake Arctic Embed M v2.0 → Snowflake Arctic Embed L v2.0
Re-embed your whole corpus›
Vectors from different models can't be mixed; dimensions change from 768 to 1,024.