Compare models
Gemma 2 9B Instruct vs DeepSeek V3 vs Llama 3.1 8B 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 | Gemma 2 9B Instruct | DeepSeek V3 | Llama 3.1 8B Instruct |
|---|---|---|---|
| Downloads, 30 days | 864,175Synced from sourceCurrent1h ago | 1,134,368Synced from sourceCurrent1h ago | 6,225,344 (highest of the compared values)Synced from sourceCurrent1h ago |
| Likes | 954Synced from sourceCurrent1h ago | 4,236Synced from sourceCurrent1h ago | 7,861 (highest of the compared values)Synced from sourceCurrent1h ago |
| Context window | — | 163,840 (highest of the compared values)Synced from sourceCurrent1h ago | 131,072Synced from sourceCurrent1h ago |
| Input, $/M tokens | — | 0.32Synced from sourceCurrent1h ago | 0.05 (lowest of the compared values)Synced from sourceCurrent1h ago |
| Modality | textSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago |
| Licence | gemmaSeeded, unreviewedwritten 29d ago | deepseekSeeded, unreviewedwritten 29d ago | llama-3.1Seeded, unreviewedwritten 29d ago |
| Gated | manualSynced from sourceCurrent1h ago | noSynced from sourceCurrent1h ago | manualSynced from sourceCurrent1h ago |
| Last updated | 2024-08-27Synced from sourceCurrent1h ago | 2025-03-27Synced from sourceCurrent1h ago | 2024-09-25Synced from sourceCurrent1h ago |
| Library | transformersSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago |
| Task | text-generationSynced from sourceCurrent1h ago | text-generationSynced from sourceCurrent1h ago | text-generationSynced from sourceCurrent1h ago |
| Hugging Face | google/gemma-2-9b-itSynced from sourceCurrent1h ago | deepseek-ai/DeepSeek-V3Synced from sourceCurrent1h ago | meta-llama/Llama-3.1-8B-InstructSynced from sourceCurrent1h ago |
| OpenRouter id | — | deepseek/deepseek-chatSynced from sourceCurrent1h ago | meta-llama/llama-3.1-8b-instructSynced from sourceCurrent1h ago |
| Output, $/M tokens | — | 0.89Synced from sourceCurrent1h ago | 0.08Synced from sourceCurrent1h ago |
| Vendor | GoogleSeeded, unreviewedwritten 29d ago | DeepSeekSeeded, unreviewedwritten 29d ago | MetaSeeded, unreviewedwritten 29d ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 1h 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.