Compare models
Phi-4 vs BGE-M3 vs Nomic Embed Text v1.5
Every figure below carries the source that reported it and the moment it was observed. Values that failed validation are withheld rather than shown, and a dash means no source we track carries that field for that model.
| Field | Phi-4 | BGE-M3 | Nomic Embed Text v1.5 |
|---|---|---|---|
| Downloads, 30 days | 293,650Synced from sourceCurrent2h ago | 30,102,339 (highest of the compared values)Synced from sourceCurrent2h ago | 11,869,224Synced from sourceCurrent2h ago |
| Likes | 2,340Synced from sourceCurrent2h ago | 3,971 (highest of the compared values)Synced from sourceCurrent2h ago | 988Synced from sourceCurrent2h ago |
| Context window | 16,384Synced from sourceCurrent2h ago | — | — |
| Input, $/M tokens | 0.07Synced from sourceCurrent2h ago | — | — |
| Modality | textSeeded, unreviewedwritten 2mo ago | embeddingSeeded, unreviewedwritten 2mo ago | embeddingSeeded, unreviewedwritten 2mo ago |
| Licence | mitSeeded, unreviewedwritten 2mo ago | mitSeeded, unreviewedwritten 2mo ago | apache-2.0Seeded, unreviewedwritten 2mo ago |
| Gated | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago |
| Last updated | 2026-07-14Synced from sourceCurrent2h ago | 2024-07-03Synced from sourceCurrent2h ago | 2026-04-07Synced from sourceCurrent2h ago |
| Library | transformersSynced from sourceCurrent2h ago | sentence-transformersSynced from sourceCurrent2h ago | sentence-transformersSynced from sourceCurrent2h ago |
| Task | text-generationSynced from sourceCurrent2h ago | sentence-similaritySynced from sourceCurrent2h ago | sentence-similaritySynced from sourceCurrent2h ago |
| Hugging Face | microsoft/phi-4Synced from sourceCurrent2h ago | BAAI/bge-m3Synced from sourceCurrent2h ago | nomic-ai/nomic-embed-text-v1.5Synced from sourceCurrent2h ago |
| OpenRouter id | microsoft/phi-4Synced from sourceCurrent2h ago | — | — |
| Output, $/M tokens | 0.14Synced from sourceCurrent2h ago | — | — |
| Vendor | MicrosoftSeeded, unreviewedwritten 2mo ago | BAAISeeded, unreviewedwritten 2mo ago | Nomic AISeeded, unreviewedwritten 2mo ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 2h ago. Where a row is marked, ▲ is the highest of the values shown and ▼ the lowest — arithmetic on the figures above, not a ranking or a recommendation. Rows where neither extreme is meaningful are left unmarked rather than given a direction they do not have.
Change the comparison
Remove one, or open the directory to pick a different set. Up to 3 at a time.