Compare models
Llama 3.1 8B Instruct vs Qwen2.5 72B Instruct vs DeepSeek R1
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 | Qwen2.5 72B Instruct | DeepSeek R1 |
|---|---|---|---|
| Downloads, 30 days | 6,225,344 (highest of the compared values)Synced from sourceCurrent2h ago | 326,043Synced from sourceCurrent2h ago | 815,126Synced from sourceCurrent2h ago |
| Likes | 7,861Synced from sourceCurrent2h ago | 994Synced from sourceCurrent2h ago | 14,285 (highest of the compared values)Synced from sourceCurrent2h ago |
| Context window | 131,072 (highest of the compared values)Synced from sourceCurrent2h ago | 32,768Synced from sourceCurrent2h ago | 64,000Synced from sourceCurrent2h ago |
| Input, $/M tokens | 0.05 (lowest of the compared values)Synced from sourceCurrent2h ago | 0.36Synced from sourceCurrent2h ago | 0.7Synced from sourceCurrent2h ago |
| Modality | textSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago | reasoningSeeded, unreviewedwritten 29d ago |
| Licence | llama-3.1Seeded, unreviewedwritten 29d ago | qwenSeeded, unreviewedwritten 29d ago | mitSeeded, unreviewedwritten 29d ago |
| Gated | manualSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago |
| Last updated | 2024-09-25Synced from sourceCurrent2h ago | 2025-01-12Synced from sourceCurrent2h ago | 2025-03-27Synced from sourceCurrent2h ago |
| Library | transformersSynced from sourceCurrent2h ago | transformersSynced from sourceCurrent2h ago | transformersSynced from sourceCurrent2h ago |
| Task | text-generationSynced from sourceCurrent2h ago | text-generationSynced from sourceCurrent2h ago | text-generationSynced from sourceCurrent2h ago |
| Hugging Face | meta-llama/Llama-3.1-8B-InstructSynced from sourceCurrent2h ago | Qwen/Qwen2.5-72B-InstructSynced from sourceCurrent2h ago | deepseek-ai/DeepSeek-R1Synced from sourceCurrent2h ago |
| OpenRouter id | meta-llama/llama-3.1-8b-instructSynced from sourceCurrent2h ago | qwen/qwen-2.5-72b-instructSynced from sourceCurrent2h ago | deepseek/deepseek-r1Synced from sourceCurrent2h ago |
| Output, $/M tokens | 0.08Synced from sourceCurrent2h ago | 0.4Synced from sourceCurrent2h ago | 2.5Synced from sourceCurrent2h ago |
| Vendor | MetaSeeded, unreviewedwritten 29d ago | AlibabaSeeded, unreviewedwritten 29d ago | DeepSeekSeeded, 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.