Compare models
Whisper large-v3 vs Phi-4 vs Gemma 2 9B 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 | Whisper large-v3 | Phi-4 | Gemma 2 9B Instruct |
|---|---|---|---|
| Downloads, 30 days | 4,712,143 (highest of the compared values)Synced from sourceCurrent1h ago | 624,150Synced from sourceCurrent1h ago | 864,175Synced from sourceCurrent1h ago |
| Likes | 6,365 (highest of the compared values)Synced from sourceCurrent1h ago | 2,309Synced from sourceCurrent1h ago | 954Synced from sourceCurrent1h ago |
| Context window | — | 16,384Synced from sourceCurrent1h ago | — |
| Input, $/M tokens | — | 0.07Synced from sourceCurrent1h ago | — |
| Modality | speechSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago |
| Licence | apache-2.0Seeded, unreviewedwritten 29d ago | mitSeeded, unreviewedwritten 29d ago | gemmaSeeded, unreviewedwritten 29d ago |
| Gated | noSynced from sourceCurrent1h ago | noSynced from sourceCurrent1h ago | manualSynced from sourceCurrent1h ago |
| Last updated | 2024-08-12Synced from sourceCurrent1h ago | 2026-07-14Synced from sourceCurrent1h ago | 2024-08-27Synced from sourceCurrent1h ago |
| Library | transformersSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago |
| Task | automatic-speech-recognitionSynced from sourceCurrent1h ago | text-generationSynced from sourceCurrent1h ago | text-generationSynced from sourceCurrent1h ago |
| Hugging Face | openai/whisper-large-v3Synced from sourceCurrent1h ago | microsoft/phi-4Synced from sourceCurrent1h ago | google/gemma-2-9b-itSynced from sourceCurrent1h ago |
| OpenRouter id | — | microsoft/phi-4Synced from sourceCurrent1h ago | — |
| Output, $/M tokens | — | 0.14Synced from sourceCurrent1h ago | — |
| Vendor | OpenAISeeded, unreviewedwritten 29d ago | MicrosoftSeeded, unreviewedwritten 29d ago | GoogleSeeded, 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.