Compare models
Qwen2.5 72B Instruct vs BGE-M3 vs Llama 3.3 70B Instruct
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 | Qwen2.5 72B Instruct | BGE-M3 | Llama 3.3 70B Instruct |
|---|---|---|---|
| Downloads, 30 days | 326,043Synced from sourceCurrent2h ago | 37,229,647 (highest of the compared values)Synced from sourceCurrent2h ago | 917,910Synced from sourceCurrent2h ago |
| Likes | 994Synced from sourceCurrent2h ago | 3,615 (highest of the compared values)Synced from sourceCurrent2h ago | 3,058Synced from sourceCurrent2h ago |
| Context window | 32,768Synced from sourceCurrent2h ago | — | 131,072 (highest of the compared values)Synced from sourceCurrent2h ago |
| Input, $/M tokens | 0.36Synced from sourceCurrent2h ago | — | 0.1 (lowest of the compared values)Synced from sourceCurrent2h ago |
| Modality | textSeeded, unreviewedwritten 29d ago | embeddingSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago |
| Licence | qwenSeeded, unreviewedwritten 29d ago | mitSeeded, unreviewedwritten 29d ago | llama-3.3Seeded, unreviewedwritten 29d ago |
| Gated | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago | manualSynced from sourceCurrent2h ago |
| Last updated | 2025-01-12Synced from sourceCurrent2h ago | 2024-07-03Synced from sourceCurrent2h ago | 2024-12-21Synced from sourceCurrent2h ago |
| Library | transformersSynced from sourceCurrent2h ago | sentence-transformersSynced from sourceCurrent2h ago | transformersSynced from sourceCurrent2h ago |
| Task | text-generationSynced from sourceCurrent2h ago | sentence-similaritySynced from sourceCurrent2h ago | text-generationSynced from sourceCurrent2h ago |
| Hugging Face | Qwen/Qwen2.5-72B-InstructSynced from sourceCurrent2h ago | BAAI/bge-m3Synced from sourceCurrent2h ago | meta-llama/Llama-3.3-70B-InstructSynced from sourceCurrent2h ago |
| OpenRouter id | qwen/qwen-2.5-72b-instructSynced from sourceCurrent2h ago | — | meta-llama/llama-3.3-70b-instructSynced from sourceCurrent2h ago |
| Output, $/M tokens | 0.4Synced from sourceCurrent2h ago | — | 0.32Synced from sourceCurrent2h ago |
| Vendor | AlibabaSeeded, unreviewedwritten 29d ago | BAAISeeded, unreviewedwritten 29d ago | MetaSeeded, unreviewedwritten 29d 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.