Video Text To Text Models
Tracked video text to text models monitored by OpenModelStats. Rankings below compare tracked models against each other — see the methodology for scope and limitations.
- Top-10 combined DL 30D
- 178K
- Tasks directory position
- See all tasks
- Growth history
- Available
- Last refresh
- Sep 22, 2026
Trending now
| # | Model | Task | DL 30D | 7D | Likes | Params |
|---|---|---|---|---|---|---|
| 1 | OneStreamer-4BMCG-NJU | Video Text To Text | 103 | — | ||
| 2 | phyjudge-9BNU-World-Model-Embodied-AI | Video Text To Text | 20 | — | ||
| 3 | JoyAI-VL-Interaction-Previewjdopensource | Video Text To Text | 318 | 0.5%(up) | ||
| 4 | StreamOPD-4B-ST-CueGateUniX-Lab | Video Text To Text | 61 | — | ||
| 5 | nemotron-labs-audio-visual-flamingo-hfnvidia | Video Text To Text | 363 | 4.2%(up) | ||
| 6 | JoyAI-VL-Interaction-INT8jdopensource | Video Text To Text | 81 | 0.8%(up) | ||
| 7 | JoyAI-VL-Interaction-INT4jdopensource | Video Text To Text | 293 | — | ||
| 8 | VideoChat3-4BMCG-NJU | Video Text To Text | 2,671 | 9.6%(up) | ||
| 9 | JoyAI-VL-Interaction-FP8jdopensource | Video Text To Text | 76 | — | ||
| 10 | JoyAI-VL-Interaction-NVFP4jdopensource | Video Text To Text | 62 | — |
Most downloaded
| Model | Task | DL 30D | 7D | Likes | Params |
|---|---|---|---|---|---|
| LLaVA-NeXT-Video-7B-hfllava-hf | Video Text To Text | 100.8K | 1.3%(up) | ||
| Keye-VL-8B-PreviewKwai-Keye | Video Text To Text | 18.3K | 0.3%(up) | ||
| RankVideohltcoe | Video Text To Text | 12.6K | 155.2%(up) | ||
| LLaVA-Video-7B-Qwen2lmms-lab | Video Text To Text | 12.3K | 0.2%(up) | ||
| Keye-VL-1_5-8BKwai-Keye | Video Text To Text | 11.9K | 0.2%(up) | ||
| SkyCaptioner-V1-GGUFMungert | Video Text To Text | 5,311 | 1.2%(up) | ||
| GenS-qwen2d5-vl-3byaolily | Video Text To Text | 4,789 | — | ||
| InternVideo2_5_Chat_8BOpenGVLab | Video Text To Text | 4,061 | 0.6%(up) | ||
| VideoLLaMA3-2BDAMO-NLP-SG | Video Text To Text | 4,036 | 2.1%(up) | ||
| VideoLLaMA3-7BDAMO-NLP-SG | Video Text To Text | 3,960 | 0.1%(up) |
Fastest growing
Downloads gained over the last seven tracked days.
| Model | Task | DL 30D | 7D7D gained | Likes | Params |
|---|---|---|---|---|---|
| LLaVA-NeXT-Video-7B-hfllava-hf | Video Text To Text | 100.8K | +38.6K | ||
| RankVideohltcoe | Video Text To Text | 12.6K | +9,289 | ||
| Keye-VL-8B-PreviewKwai-Keye | Video Text To Text | 18.3K | +4,861 | ||
| Keye-VL-1_5-8BKwai-Keye | Video Text To Text | 11.9K | +3,056 | ||
| LLaVA-Video-7B-Qwen2lmms-lab | Video Text To Text | 12.3K | +2,997 | ||
| VideoLLaMA3-2BDAMO-NLP-SG | Video Text To Text | 4,036 | +2,470 | ||
| VideoLLaMA3-7BDAMO-NLP-SG | Video Text To Text | 3,960 | +1,862 | ||
| InternVideo2_5_Chat_8BOpenGVLab | Video Text To Text | 4,061 | +1,587 | ||
| Marlin-2BNemoStation | Video Text To Text | 2,911 | +715 | ||
| VideoChat3-4BMCG-NJU | Video Text To Text | 2,671 | +677 |
New & notable
Published within the last 90 days with meaningful traction.
| Model | Task | DL 30D | 7D7D gained | Likes | Params | Published |
|---|---|---|---|---|---|---|
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUFprithivMLmods | Video Text To Text | 2,172 | +482 | Aug 10, 2026 | ||
| TimeLens2-4BMCG-NJU | Video Text To Text | 1,604 | — | Jul 12, 2026 | ||
| MOSS-VL-Instruct-0708-FP8OpenMOSS-Team | Video Text To Text | 1,557 | +19 | Aug 7, 2026 | ||
| TimeLens2-8BMCG-NJU | Video Text To Text | 1,545 | +333 | Jul 12, 2026 | ||
| MOSS-VL-RealtimeOpenMOSS-Team | Video Text To Text | 1,201 | +247 | Jul 14, 2026 | ||
| VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUFprithivMLmods | Video Text To Text | 1,081 | +183 | Aug 10, 2026 | ||
| MOSS-VL-Instruct-0708OpenMOSS-Team | Video Text To Text | 865 | +69 | Jul 13, 2026 | ||
| JoyAI-VL-Interactionjdopensource | Video Text To Text | 590 | +132 | Jul 21, 2026 | ||
| Video-ORA-4B-GGUFprithivMLmods | Video Text To Text | 521 | +0 | Aug 30, 2026 | ||
| Video-ORA-9B-GGUFprithivMLmods | Video Text To Text | 507 | +0 | Aug 30, 2026 |