Cosmos-Reason2-8B
nvidia/Cosmos-Reason2-8B
Tracked by OpenModelStats since September 9, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 167K
- Total downloadsCumulative all-time download counter reported by the source platform.
- 2.2M
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +83.3K(increase)
- 4.0%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 236
- +5 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #267 among tracked Image Text to Text models.
- #1,728
- 4(up 4 places)this week
- Parameters
- 8.8B
- Last source update
- Apr 30, 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.
- 93.1
- Cosmos-Reason2-8B gained 83.3K downloads during the last seven tracked days.
- It moved from #268 to #267 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
Cosmos-Reason2-8B is a image text to text model published by nvidia. OpenModelStats has tracked the model since Sep 9, 2026, most recently observing it 10h ago.
- Published
- Dec 12, 2025
- Last updated
- Apr 30, 2026
- Library
- cosmos
- License
- other
- Task
- Image Text to Text
- Parameters
- 8,767,123,696
- Spaces
- —
- Derivative models
- 2
- Velocity 7D/day
- 11.9K
cosmossafetensorsqwen3_vlnvidiaconversationalimage-text-to-textarxiv:2503.06800arxiv:2406.10721arxiv:2603.18178arxiv:2312.14115base_model:Qwen/Qwen3-VL-8B-Instructbase_model:finetune:Qwen/Qwen3-VL-8B-Instruct
Publisher
nvidiaView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Base model
Derivative models
Sibling models
Similar models
| Model | DL 30D |
|---|---|
| Qwen3-VL-8B-InstructQwen | 9.7M |
| chandradatalab-to | 356.5K |
| Qwen3-VL-8B-ThinkingQwen | 140.4K |
| XCurOS1.2-8B-VLBF16-InstructXCurOS | 91.6K |
| qwen3vl-resume-parsersukhrobnurali | 87.9K |
| Huihui-Qwen3-VL-8B-Instruct-abliteratedhuihui-ai | 32.1K |