Migician
Michael4933/Migician
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 447
- Total downloadsCumulative all-time download counter reported by the source platform.
- 8,588
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +342(increase)
- 4.2%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 1
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #4068 among tracked Image Text to Text models.
- #42,820
- 180(down 180 places)this week
- Parameters
- 8.3B
- Last source update
- May 21, 2025
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 50.4
- Migician gained 342 downloads during the last seven tracked days.
- It moved from #4057 to #4068 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
Migician is a image text to text model published by Michael4933. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 3, 2026.
- Published
- Jan 1, 2025
- Last updated
- May 21, 2025
- Library
- transformers
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 8,291,375,616
- Spaces
- 1
- Derivative models
- —
- Velocity 7D/day
- 49
transformerssafetensorsqwen2_vlimage-text-to-textconversationalendataset:Michael4933/MGrounding-630kdataset:lmms-lab/M4-Instruct-Datadataset:lmms-lab/LLaVA-OneVision-Dataarxiv:2501.05767base_model:Qwen/Qwen2-VL-7B-Instructbase_model:finetune:Qwen/Qwen2-VL-7B-Instruct
Model family
Based on base-model relationships reported by the source's metadata.
Base model
- Qwen2-VL-7B-Instruct622.6K
Similar models
| Model | DL 30D |
|---|---|
| Qwen2-VL-7B-Instruct-AWQQwen | 1.6M |
| Qwen2-VL-7B-InstructQwen | 622.6K |
| olmOCR-7B-0225-previewallenai | 65.4K |
| Qwen2-VL-7B-Instructunsloth | 3,683 |
| minecraft-openha-qwen2vl-7b-2509CraftJarvis | 3,262 |
| AINMBZUAI | 1,889 |