OpenModelStats

Qwen3-VisionCaption-2B

prithivMLmods/Qwen3-VisionCaption-2B

Image Text to Text2.1B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since October 3, 2026View on Hugging Face ↗
Downloads 30D
66
Total downloads
648
Gained 7D
—
Gained 30D
—
Likes
6
Rank · tracked models
#55,218
275(down 275 places)this week
Parameters
2.1B
Last source update
Nov 29, 2025
  • It moved from #5014 to #5042 among tracked Image Text to Text models this week.
7D30D90D1YAll
Total downloadsGained per dayRolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-VisionCaption-2B is a image text to text model published by prithivMLmods. OpenModelStats has tracked the model since Oct 3, 2026, most recently observing it Oct 6, 2026.

Published
Nov 28, 2025
Last updated
Nov 29, 2025
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
2,127,532,032
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen3_vlimage-text-to-texttext-generation-inferenceimage-captionabliterateduncensoredllama.cppconversationalenzh

Publisher

prithivMLmodsView publisher statistics →

Derived from prithivMLmods/Qwen3-VL-2B-Instruct-abliterated-v1 (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-VisionCaption-2B
ModelDL 30D
Qwen3-VL-2B-InstructQwen2.8M
typhoon-ocr1.5-2btyphoon-ai369.6K
Qwen3-VL-2B-ThinkingQwen114K
Qwen3-VL-2B-Instructunsloth6,746
Qwen3-VL-2B-Instruct-4bitmlx-community3,185
Qwen3-VL-2B-Thinkingfuriosa-ai2,621