LLaVA-OneVision-1.5-4B-Instruct
lmms-lab/LLaVA-OneVision-1.5-4B-Instruct
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 1,005
- Total downloadsCumulative all-time download counter reported by the source platform.
- 37K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +87(increase)
- 0.2%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 18
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #3098 among tracked Image Text to Text models.
- #32,871
- 98(down 98 places)this week
- Parameters
- 4.7B
- Last source update
- Jul 16, 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.
- 29.5
- LLaVA-OneVision-1.5-4B-Instruct gained 87 downloads during the last seven tracked days.
- It moved from #3072 to #3098 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
LLaVA-OneVision-1.5-4B-Instruct is a image text to text model published by lmms-lab. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 4, 2026.
- Published
- Sep 26, 2025
- Last updated
- Jul 16, 2026
- Library
- transformers
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 4,741,610,528
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 12
transformerstensorboardsafetensorsfeature-extractionimage-text-to-textconversationalcustom_codedataset:lmms-lab/LLaVA-One-Vision-1.5-Mid-Training-85Mdataset:lmms-lab/LLaVA-OneVision-1.5-Insturct-Datadataset:HuggingFaceM4/FineVisionarxiv:2509.23661base_model:DeepGlint-AI/rice-vit-large-patch14-560
Publisher
lmms-labView publisher statistics →Derived from DeepGlint-AI/rice-vit-large-patch14-560 (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Mage-VLmicrosoft | 10.9K |
| Mage-VL-8bitmlx-community | 233 |
| Qianfan-OCRbaidu | 247.3K |
| QianfanOCRbairongz | 1,066 |
| Qwen3.5-4B-AWQ-BF16-INT8cyankiwi | 380 |
| Qwen3.5-4B-AWQ-BF16-INT4cyankiwi | 284 |