Compare models
DeepSeek V3 vs DeepSeek R1 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 | DeepSeek V3 | DeepSeek R1 | Llama 3.3 70B Instruct |
|---|---|---|---|
| Downloads, 30 days | 1,163,331 (highest of the compared values)Synced from sourceCurrent3h ago | 895,329Synced from sourceCurrent3h ago | 904,760Synced from sourceCurrent3h ago |
| Likes | 4,308Synced from sourceCurrent3h ago | 14,298 (highest of the compared values)Synced from sourceCurrent3h ago | 3,066Synced from sourceCurrent3h ago |
| Context window | 163,840 (highest of the compared values)Synced from sourceCurrent3h ago | 64,000Synced from sourceCurrent3h ago | 131,072Synced from sourceCurrent3h ago |
| Input, $/M tokens | 0.26Synced from sourceCurrent3h ago | 0.7Synced from sourceCurrent3h ago | 0.1 (lowest of the compared values)Synced from sourceCurrent3h ago |
| Modality | textSeeded, unreviewedwritten 1mo ago | reasoningSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago |
| Licence | deepseekSeeded, unreviewedwritten 1mo ago | mitSeeded, unreviewedwritten 1mo ago | llama-3.3Seeded, unreviewedwritten 1mo ago |
| Gated | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | manualSynced from sourceCurrent3h ago |
| Last updated | 2025-03-27Synced from sourceCurrent3h ago | 2025-03-27Synced from sourceCurrent3h ago | 2024-12-21Synced from sourceCurrent3h ago |
| Library | transformersSynced from sourceCurrent3h ago | transformersSynced from sourceCurrent3h ago | transformersSynced from sourceCurrent3h ago |
| Task | text-generationSynced from sourceCurrent3h ago | text-generationSynced from sourceCurrent3h ago | text-generationSynced from sourceCurrent3h ago |
| Hugging Face | deepseek-ai/DeepSeek-V3Synced from sourceCurrent3h ago | deepseek-ai/DeepSeek-R1Synced from sourceCurrent3h ago | meta-llama/Llama-3.3-70B-InstructSynced from sourceCurrent3h ago |
| OpenRouter id | deepseek/deepseek-chatSynced from sourceCurrent3h ago | deepseek/deepseek-r1Synced from sourceCurrent3h ago | meta-llama/llama-3.3-70b-instructSynced from sourceCurrent3h ago |
| Output, $/M tokens | 1.03Synced from sourceCurrent3h ago | 2.5Synced from sourceCurrent3h ago | 0.32Synced from sourceCurrent3h ago |
| Vendor | DeepSeekSeeded, unreviewedwritten 1mo ago | DeepSeekSeeded, unreviewedwritten 1mo ago | MetaSeeded, unreviewedwritten 1mo ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 3h 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.