ZwZ-4B
inclusionAI/ZwZ-4B
Tracked by OpenModelStats since September 26, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 246
- Total downloadsCumulative all-time download counter reported by the source platform.
- 5,490
- 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.
- 34
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #4652 among tracked Image Text to Text models.
- #50,167
- 394(down 394 places)this week
- Parameters
- 4.8B
- Last source update
- Mar 4, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 0.0
- It moved from #4623 to #4652 among tracked Image Text to Text models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
ZwZ-4B is a image text to text model published by inclusionAI. OpenModelStats has tracked the model since Sep 26, 2026, most recently observing it Oct 1, 2026.
- Published
- Feb 12, 2026
- Last updated
- Mar 4, 2026
- Library
- transformers
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 4,826,771,968
- Spaces
- —
- Derivative models
- 1
- Velocity 7D/day
- —
transformerssafetensorsqwen3_vlimage-text-to-textconversationalendataset:inclusionAI/ZoomBenchdataset:inclusionAI/ZwZ-RL-VQAarxiv:2602.11858base_model:Qwen/Qwen3-VL-4B-Instructbase_model:finetune:Qwen/Qwen3-VL-4B-Instructlicense:apache-2.0
Publisher
inclusionAIView publisher statistics →Derived from Qwen/Qwen3-VL-4B-Instruct (reported by the source; parent not yet tracked).
Model family
Based on base-model relationships reported by the source's metadata.
Derivative models
Similar models
| Model | DL 30D |
|---|---|
| Robo-Dopamine-GRM-2.0-4B-Previewtanhuajie2001 | 2,215 |
| Qwen3-VL-4B-Instruct-FP8Qwen | 265.5K |
| Qwen3-VL-4B-Thinking-FP8Qwen | 1,004 |
| Qwen3-VL-4B-Thinking-FP8unsloth | 80 |
| Qwen3.5-VL-4B-JANG_4S-CRACKdealignai | 329 |
| Hulu-Med-4BZJU-AI4H | 3,133 |