ns
← All models

Llama-3.2-90B-Vision-Instruct

llama

Large open multimodal Llama model for image reasoning, document QA, and captioning

Family
llama
Providers
1
Context
128,000
Output
4,096
Knowledge
2023-12
Weights
Open
Input
textimage
Output
text
Release date
2024-09-25
Updated
2024-09-25

Providers

Source: models.dev