Roboflow

Llama 3.2 Vision 90b vs Llama 4 Maverick

Compare Llama 3.2 Vision 90b and Llama 4 Maverick side-by-side. See how these vision models stack up in Image Captioning, OCR, and Open Prompt.

Compare Llama 3.2 Vision 90b vs Llama 4 Maverick live

Run the same image across every model that supports a task and compare their outputs side-by-side.

Extract and compare text from images across multiple models.

Open OCR in the full playground
MetaLlama 3.2 Vision 90b

Llama 3.2 Vision 90b is deprecated and can no longer be run. Details and evals are still available on its model page.

MetaLlama 4 Maverick
Run to compare this model.

Models in this comparison

Llama 3.2 Vision 90b vs Llama 4 Maverick Comparison Table

Evals updated August 20, 2026Pricing updated August 24, 2026

PropertyLlama 3.2 Vision 90bLlama 4 Maverick
OrganizationMetaMeta
Categoryopenopen
Modalitymultimodalmultimodal
Release DateSep 2024Apr 2025
Context Window128K1.0M
Parameters90B400B
LicenseProprietaryCustom
Pricing per 1M tokens
Input $/1M$0.200
Output $/1M$0.800
Vision Tasks
CaptioningDemo
Chart Question Answering
Classification
Document Question Answering
Image Tagging
Multi-Label Classification
OCRDemo
Vision Language
Visual Question AnsweringDemo
Object Detection
Model Features
Foundation Vision
LLMs with Vision Capabilities
Multimodal Vision

Llama 3.2 Vision 90b vs Llama 4 Maverick: Overview

Llama 3.2 Vision 90b

Llama 3.2 Vision 90B, released by Meta AI on September 25, 2024, is the largest vision-capable model in the Llama 3.2 family. With about 90 billion parameters (~88.8B) and a 128,000-token context window, it is designed for high-performance multimodal reasoning over images and text, while producing only text outputs. The model was trained on ~6 billion image–text pairs and instruction-tuned (SFT + RLHF), with a knowledge cutoff of December 2023.

It powers tasks like visual question answering, captioning, and image-grounded reasoning, and achieves strong benchmark performance compared to both open and proprietary models. The model officially supports English for multimodal (image+text) tasks, while text-only inputs extend to eight languages (including German, French, Hindi, and Spanish). Due to its large parameter size, it requires substantial compute resources but is accessible via cloud providers like Amazon Bedrock, Oracle Cloud, and Azure AI Foundry. While highly capable, it is limited to text-only outputs and has stricter multilingual support for vision-based inputs.

Llama 4 Maverick

Llama 4 Maverick, introduced on April 5, 2025, is one of the first models in Meta’s Llama 4 family, designed as a natively multimodal model supporting text + image inputs with text outputs. It employs a Mixture-of-Experts (MoE) architecture with 128 experts, activating ~17B parameters per token out of a pool of ~400B total parameters. This design improves scalability, efficiency, and reasoning capacity. Maverick has a 1M-token context window, enabling it to handle large documents, extended conversations, and multimodal reasoning. Its knowledge cutoff is August 2024.

The model is released under the Llama 4 Community License and comes in both base and instruction-tuned (“Instruct”) versions. Maverick is widely deployed via Hugging Face, Google Vertex AI, Amazon Bedrock, and Oracle Cloud, making it one of the most accessible large open-weight models. However, it outputs text only (no image/audio generation) and, while input capacity is huge, output limits are typically much smaller. The MoE design also raises hardware demands, as maintaining 128 experts requires significant compute resources, and Meta’s license introduces restrictions around commercial-scale use.