DeepSeek-V4-Flash-Vision-Exp

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Image Text to Text305B parameterstransformersLicense: mit
Tracked by OpenModelStats since October 8, 2026View on Hugging Face ↗
Downloads 30D
539.2K
Total downloads
1.1M
Gained 7D
+255.2K(increase)
46.6%(up) vs baseline
Gained 30D
—
Likes
951
+24 in 7D
Rank · tracked models
#709
37(down 37 places)this week
Parameters
305B
Last source update
Sep 1, 2026
Momentum
99.2
  • DeepSeek-V4-Flash-Vision-Exp gained 255.2K downloads during the last seven tracked days.
  • It moved from #114 to #120 among tracked Image Text to Text models this week.
  • The model earned 24 new likes over the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

DeepSeek-V4-Flash-Vision-Exp is a image text to text model published by deepseek-ai. OpenModelStats has tracked the model since Oct 8, 2026, most recently observing it 23h ago.

Published
Aug 31, 2026
Last updated
Sep 1, 2026
Library
transformers
License
mit
Task
Image Text to Text
Parameters
304,646,824,126
Spaces
—
Derivative models
—
Velocity 7D/day
36.5K
transformerssafetensorsdeepseek_v4text-generationimage-text-to-textlicense:miteval-resultsendpoints_compatible8-bitfp8region:us

Similar models