ClipTagger-12b

inference-net/ClipTagger-12b

Image Text to Text12.2B parametersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
60
Total downloads
6,576
Gained 7D
+8(increase)
0.1%(up) vs baseline
Gained 30D
—
Likes
59
+0 in 7D
Rank · tracked models
#54,138
362(down 362 places)this week
Parameters
12.2B
Last source update
Aug 14, 2025
Momentum
20.5
  • ClipTagger-12b gained 8 downloads during the last seven tracked days.
  • It moved from #4927 to #4945 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

ClipTagger-12b is a image text to text model published by inference-net. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 4, 2026.

Published
Aug 13, 2025
Last updated
Aug 14, 2025
Library
—
License
apache-2.0
Task
Image Text to Text
Parameters
12,189,561,456
Spaces
—
Derivative models
—
Velocity 7D/day
1
safetensorsgemma3VLMvideo-understandingimage-captioninggemmajson-modestructured-outputvideo-analysisimage-text-to-textconversationalen

Similar models

Models similar to ClipTagger-12b
ModelDL 30D
gemma-3-12b-it-FP8-dynamicRedHatAI1,996
gemma-3-12b-itgoogle492K
gemma-3-12b-it-int4-awqgaunernst154.9K
gemma-3-12b-ptgoogle34.6K
gemma-3-12b-it-qat-q4_0-unquantizedLightricks20.8K
gemma-3-12b-itunsloth17.1K
inference-net/ClipTagger-12b — Downloads, Growth & Stats | OpenModelStats