Compare models
Llama 3.1 8B Instruct vs Mixtral 8x7B Instruct vs DeepSeek V3
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 | Llama 3.1 8B Instruct | Mixtral 8x7B Instruct | DeepSeek V3 |
|---|---|---|---|
| Downloads, 30 days | 6,107,664 (highest of the compared values)Synced from sourceCurrent5h ago | 207,778Synced from sourceCurrent5h ago | 1,163,331Synced from sourceCurrent5h ago |
| Likes | 7,988 (highest of the compared values)Synced from sourceCurrent5h ago | 4,757Synced from sourceCurrent5h ago | 4,308Synced from sourceCurrent5h ago |
| Context window | 131,072Synced from sourceCurrent5h ago | — | 163,840 (highest of the compared values)Synced from sourceCurrent5h ago |
| Input, $/M tokens | 0.05 (lowest of the compared values)Synced from sourceCurrent5h ago | — | 0.26Synced from sourceCurrent5h ago |
| Modality | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago |
| Licence | llama-3.1Seeded, unreviewedwritten 1mo ago | apache-2.0Seeded, unreviewedwritten 1mo ago | deepseekSeeded, unreviewedwritten 1mo ago |
| Gated | manualSynced from sourceCurrent5h ago | noSynced from sourceCurrent5h ago | noSynced from sourceCurrent5h ago |
| Last updated | 2024-09-25Synced from sourceCurrent5h ago | 2025-07-24Synced from sourceCurrent5h ago | 2025-03-27Synced from sourceCurrent5h ago |
| Library | transformersSynced from sourceCurrent5h ago | vllmSynced from sourceCurrent5h ago | transformersSynced from sourceCurrent5h ago |
| Task | text-generationSynced from sourceCurrent5h ago | — | text-generationSynced from sourceCurrent5h ago |
| Hugging Face | meta-llama/Llama-3.1-8B-InstructSynced from sourceCurrent5h ago | mistralai/Mixtral-8x7B-Instruct-v0.1Synced from sourceCurrent5h ago | deepseek-ai/DeepSeek-V3Synced from sourceCurrent5h ago |
| OpenRouter id | meta-llama/llama-3.1-8b-instructSynced from sourceCurrent5h ago | — | deepseek/deepseek-chatSynced from sourceCurrent5h ago |
| Output, $/M tokens | 0.08Synced from sourceCurrent5h ago | — | 1.03Synced from sourceCurrent5h ago |
| Vendor | MetaSeeded, unreviewedwritten 1mo ago | Mistral AISeeded, unreviewedwritten 1mo ago | DeepSeekSeeded, unreviewedwritten 1mo ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 5h 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.