Video-optim

ContentLens-AI/Video-optim

Image Text to Text4.8B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 17, 2026View on Hugging Face ↗
Downloads 30D
328
Total downloads
2,671
Gained 7D
—
Gained 30D
—
Likes
2
Rank · tracked models
#48,367
389(down 389 places)this week
Parameters
4.8B
Last source update
May 28, 2026
Momentum
0.0
  • It moved from #4505 to #4539 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

Video-optim is a image text to text model published by ContentLens-AI. OpenModelStats has tracked the model since Sep 17, 2026, most recently observing it Sep 23, 2026.

Published
Mar 24, 2026
Last updated
May 28, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
4,774,635,422
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen3_5image-text-to-textconversationalbase_model:Qwen/Qwen3.5-4Bbase_model:quantized:Qwen/Qwen3.5-4Blicense:apache-2.0endpoints_compatiblecompressed-tensorsregion:us

Publisher

ContentLens-AIView publisher statistics →

Derived from Qwen/Qwen3.5-4B (reported by the source; parent not yet tracked).

Similar models

Models similar to Video-optim
ModelDL 30D
Qwen3.5-4B-AWQ-4bitcyankiwi381.3K
Qwen3.5-4B-AWQ-INT8-INT4cyankiwi662
gemma-4-E4B-it-AWQ-4bitChunity1,928
Qwen3.5-4B-AWQ-BF16-INT8cyankiwi359
Qwen3.5-4B-AWQ-BF16-INT4cyankiwi261
Mage-VLmicrosoft10.4K
ContentLens-AI/Video-optim — Downloads, Growth & Stats | OpenModelStats