Llama 3.2 90B Vision Instruct
The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in image captioning, visual question answering, and advanced image-text comprehension.
Input
Output
Context
33K
Max Output
16K
Parameters
90B
Technical Specifications
Model TypeVision
Context Window33K
Max Output Tokens16K
Parameters90B
Training Cutoff—
Licensellama3.2
Capabilities
Input Modalities
textimage
Output Modalities
text
Features
function_callingimage_understandingjson_modereasoningstreamingtext_generationvision
Benchmarks
#66
Rank (Vision)
+7/-7
arena vision ci 95
1047
Arena Score (Vision)
8,829
Votes (Vision)
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: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.