Compare models
Gemma 2 9B Instruct vs DeepSeek V3 vs GPT-4o
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 | GPT-4o |
|---|---|---|---|
| Downloads, 30 days | 113,563Synced from sourceCurrent3h ago | 1,571,257 (highest of the compared values)Synced from sourceCurrent3h ago | — |
| Likes | 1,166Synced from sourceCurrent3h ago | 4,462 (highest of the compared values)Synced from sourceCurrent3h ago | — |
| Context window | — | 163,840 (highest of the compared values)Synced from sourceCurrent3h ago | 128,000Synced from sourceCurrent3h ago |
| Input, $/M tokens | — | 0.32 (lowest of the compared values)Synced from sourceCurrent3h ago | 2.5Synced from sourceCurrent3h ago |
| Modality | textSeeded, unreviewedwritten 2mo ago | textSeeded, unreviewedwritten 2mo ago | textSeeded, unreviewedwritten 2mo ago |
| Licence | gemmaSeeded, unreviewedwritten 2mo ago | deepseekSeeded, unreviewedwritten 2mo ago | proprietarySeeded, unreviewedwritten 2mo ago |
| Gated | manualSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | — |
| Last updated | 2024-08-27Synced from sourceCurrent3h ago | 2025-03-27Synced from sourceCurrent3h ago | — |
| Library | transformersSynced from sourceCurrent3h ago | transformersSynced from sourceCurrent3h ago | — |
| Task | text-generationSynced from sourceCurrent3h ago | text-generationSynced from sourceCurrent3h ago | — |
| Hugging Face | google/gemma-2-9b-itSynced from sourceCurrent3h ago | deepseek-ai/DeepSeek-V3Synced from sourceCurrent3h ago | — |
| OpenRouter id | — | deepseek/deepseek-chatSynced from sourceCurrent3h ago | openai/gpt-4oSynced from sourceCurrent3h ago |
| Output, $/M tokens | — | 0.89Synced from sourceCurrent3h ago | 10Synced from sourceCurrent3h ago |
| Vendor | GoogleSeeded, unreviewedwritten 2mo ago | DeepSeekSeeded, unreviewedwritten 2mo ago | OpenAISeeded, unreviewedwritten 2mo 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.