Llama-3.2-90B-Vision-Instruct

meta-llama/Llama-3.2-90B-Vision-Instruct

Image Text to Text88.6B parameterstransformersLicense: llama3.2Gated
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
Downloads 30D
1,468
Total downloads
1M
Gained 7D
+83(increase)
0.0%(up) vs baseline
Gained 30D
—
Likes
364
+2 in 7D
Rank · tracked models
#28,649
5781(down 5781 places)this week
Parameters
88.6B
Last source update
Mar 4, 2025
Momentum
48.8
  • Llama-3.2-90B-Vision-Instruct gained 83 downloads during the last seven tracked days.
  • It moved from #2173 to #2519 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

Llama-3.2-90B-Vision-Instruct is a image text to text model published by meta-llama. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Oct 7, 2026.

Published
Sep 19, 2024
Last updated
Mar 4, 2025
Library
transformers
License
llama3.2
Task
Image Text to Text
Parameters
88,593,355,323
Spaces
—
Derivative models
—
Velocity 7D/day
12
transformerssafetensorsmllamaimage-text-to-textfacebookmetapytorchllamallama-3conversationalende

Similar models

meta-llama/Llama-3.2-90B-Vision-Instruct — Downloads, Growth & Stats | OpenModelStats