Haru-4B
higurashi-ai/Haru-4B
Tracked by OpenModelStats since November 13, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 6,266
- Total downloadsCumulative all-time download counter reported by the source platform.
- 6,266
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- —
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 1,924
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #28 among tracked Audio to Audio models.
- #12,398
- 10260(up 10260 places)this week
- Parameters
- 5.3B
- Last source update
- Nov 13, 2026
- It moved from #41 to #28 among tracked Audio to Audio models this week.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
Haru-4B is a audio to audio model published by higurashi-ai. OpenModelStats has tracked the model since Nov 13, 2026, most recently observing it 8h ago.
- Published
- Nov 12, 2026
- Last updated
- Nov 13, 2026
- Library
- —
- License
- apache-2.0
- Task
- Audio to Audio
- Parameters
- 5,270,000,897
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
safetensorsharuspeechfull-duplexspeech-to-speechaudio-to-audioenesptdefrzh
Similar models
| Model | DL 30D |
|---|---|
| MuLaCoverHeartMuLa | 779 |
| moshika-rl-seamlesskyutai | 595 |
| moshika-rag-pytorch-bf16kyutai | 971 |
| Step-Audio-EditX-8bitmlx-community | 36 |
| Step-Audio-EditX-bf16mlx-community | 22 |
| Voila-chatmaitrix-org | 36 |