Llama 3.2 90B Vision Instruct
Meta AI's Llama 3.2 90B Vision Instruct is a multimodal large language model optimized for visual recognition, image reasoning, captioning, and answering general questions about an image, with capabilities including function calling, image understanding, and text generation. It is genuinely best at tasks that require integration of text and image inputs, such as image reasoning and captioning.
Input
Output
Context
128K
Max Output
128K
Parameters
88.6B
Technical Specifications
Model TypeChat
Context Window128,000 tokens
Max Output Tokens128,000 tokens
Parameters88.6B
Release DateSep 19, 2024
Training CutoffDec 1, 2023
Licensellama3.2
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Llama 3.2 90B Vision Instruct
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.