Compare models
Mixtral 8x7B Instruct vs Phi-4 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 | Mixtral 8x7B Instruct | Phi-4 | Llama 3.3 70B Instruct |
|---|---|---|---|
| Downloads, 30 days | 207,778Synced from sourceCurrent4h ago | 591,256Synced from sourceCurrent4h ago | 904,760 (highest of the compared values)Synced from sourceCurrent4h ago |
| Likes | 4,757 (highest of the compared values)Synced from sourceCurrent4h ago | 2,312Synced from sourceCurrent4h ago | 3,066Synced from sourceCurrent4h ago |
| Context window | — | 16,384Synced from sourceCurrent4h ago | 131,072 (highest of the compared values)Synced from sourceCurrent4h ago |
| Input, $/M tokens | — | 0.07 (lowest of the compared values)Synced from sourceCurrent4h ago | 0.1Synced from sourceCurrent4h ago |
| Modality | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago |
| Licence | apache-2.0Seeded, unreviewedwritten 1mo ago | mitSeeded, unreviewedwritten 1mo ago | llama-3.3Seeded, unreviewedwritten 1mo ago |
| Gated | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago | manualSynced from sourceCurrent4h ago |
| Last updated | 2025-07-24Synced from sourceCurrent4h ago | 2026-07-14Synced from sourceCurrent4h ago | 2024-12-21Synced from sourceCurrent4h ago |
| Library | vllmSynced from sourceCurrent4h ago | transformersSynced from sourceCurrent4h ago | transformersSynced from sourceCurrent4h ago |
| Task | — | text-generationSynced from sourceCurrent4h ago | text-generationSynced from sourceCurrent4h ago |
| Hugging Face | mistralai/Mixtral-8x7B-Instruct-v0.1Synced from sourceCurrent4h ago | microsoft/phi-4Synced from sourceCurrent4h ago | meta-llama/Llama-3.3-70B-InstructSynced from sourceCurrent4h ago |
| OpenRouter id | — | microsoft/phi-4Synced from sourceCurrent4h ago | meta-llama/llama-3.3-70b-instructSynced from sourceCurrent4h ago |
| Output, $/M tokens | — | 0.14Synced from sourceCurrent4h ago | 0.32Synced from sourceCurrent4h ago |
| Vendor | Mistral AISeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago | MetaSeeded, 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.