DuplexJev-4B
adventists-ai/DuplexJev-4B
Tracked by OpenModelStats since October 18, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 80
- Total downloadsCumulative all-time download counter reported by the source platform.
- 80
- 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
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- —
- –this week
- Parameters
- 4.2B
- Last source update
- Oct 14, 2026
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-10-18. Charts appear as daily observations accumulate.
Overview
DuplexJev-4B is a audio text to text model published by adventists-ai. OpenModelStats has tracked the model since Oct 18, 2026, most recently observing it Oct 14, 2026.
- Published
- Sep 28, 2026
- Last updated
- Oct 14, 2026
- Library
- vllm
- License
- cc-by-nc-4.0
- Task
- Audio Text To Text
- Parameters
- 4,219,708,800
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
vllmsafetensorsultravoxduplexjevspeech-to-decisionfull-duplexspeech-llmparalinguisticsaudio-text-to-textzhenarxiv:2610.02638
Publisher
adventists-aiView publisher statistics →Derived from Qwen/Qwen3-4B (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| DuplexJev-4B-Paraadventists-ai | 484 |
| AudioJevshlv | 479 |
| Borealis-5b-itVikhrmodels | 969 |
| MOSS-Audio-4B-InstructOpenMOSS-Team | 2,339 |
| MOSS-Audio-4B-ThinkingOpenMOSS-Team | 718 |
| GaussianMindBAAI | 66 |