Compare models
Mixtral 8x7B Instruct vs Llama 3.1 8B Instruct vs BGE-M3
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 | Mixtral 8x7B Instruct | Llama 3.1 8B Instruct | BGE-M3 |
|---|---|---|---|
| Downloads, 30 days | 207,778Synced from sourceCurrent4h ago | 6,107,664Synced from sourceCurrent4h ago | 36,333,889 (highest of the compared values)Synced from sourceCurrent4h ago |
| Likes | 4,757Synced from sourceCurrent4h ago | 7,988 (highest of the compared values)Synced from sourceCurrent4h ago | 3,704Synced from sourceCurrent4h ago |
| Context window | — | 131,072Synced from sourceCurrent4h ago | — |
| Input, $/M tokens | — | 0.05Synced from sourceCurrent4h ago | — |
| Modality | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago | embeddingSeeded, unreviewedwritten 1mo ago |
| Licence | apache-2.0Seeded, unreviewedwritten 1mo ago | llama-3.1Seeded, unreviewedwritten 1mo ago | mitSeeded, unreviewedwritten 1mo ago |
| Gated | noSynced from sourceCurrent4h ago | manualSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago |
| Last updated | 2025-07-24Synced from sourceCurrent4h ago | 2024-09-25Synced from sourceCurrent4h ago | 2024-07-03Synced from sourceCurrent4h ago |
| Library | vllmSynced from sourceCurrent4h ago | transformersSynced from sourceCurrent4h ago | sentence-transformersSynced from sourceCurrent4h ago |
| Task | — | text-generationSynced from sourceCurrent4h ago | sentence-similaritySynced from sourceCurrent4h ago |
| Hugging Face | mistralai/Mixtral-8x7B-Instruct-v0.1Synced from sourceCurrent4h ago | meta-llama/Llama-3.1-8B-InstructSynced from sourceCurrent4h ago | BAAI/bge-m3Synced from sourceCurrent4h ago |
| OpenRouter id | — | meta-llama/llama-3.1-8b-instructSynced from sourceCurrent4h ago | — |
| Output, $/M tokens | — | 0.08Synced from sourceCurrent4h ago | — |
| Vendor | Mistral AISeeded, unreviewedwritten 1mo ago | MetaSeeded, unreviewedwritten 1mo ago | BAAISeeded, unreviewedwritten 1mo ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 4h 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.