Roboflow

Llama 3.2 Vision 90b vs Qwen3.5 122B A10B

Compare Llama 3.2 Vision 90b and Qwen3.5 122B A10B side-by-side. See how these vision models stack up in Image Captioning, OCR, and Open Prompt.

Compare Llama 3.2 Vision 90b vs Qwen3.5 122B A10B 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.

QwenQwen3.5 122B A10B
Run to compare this model.

Models in this comparison

Llama 3.2 Vision 90b vs Qwen3.5 122B A10B Comparison Table

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

PropertyLlama 3.2 Vision 90bQwen3.5 122B A10B
OrganizationMetaQwen
Categoryopenopen
Modalitymultimodalmultimodal
Release DateSep 2024Feb 2026
Context Window128K256K
Parameters90B122B
LicenseProprietaryApache 2.0
Pricing per 1M tokens
Input $/1M$0.260
Output $/1M$2.08
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 Qwen3.5 122B A10B: 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.

Qwen3.5 122B A10B

Qwen3.5-122B-A10B is a high-capacity multimodal Mixture-of-Experts (MoE) model developed by Alibaba’s Qwen team as part of the Qwen3.5 model family. The architecture contains 122 billion total parameters while activating roughly 10 billion per token through sparse expert routing, allowing the model to balance large-scale reasoning ability with relatively efficient inference compared to dense models of similar size.

The model is designed to process both text and visual inputs within a unified multimodal framework, enabling tasks that require reasoning across images, documents, charts, and natural language. This makes it suitable for applications such as document understanding, diagram interpretation, and complex visual question answering.

Qwen3.5-122B-A10B supports a native context window of approximately 256,000 tokens, which can be extended further through techniques such as YaRN scaling to support very long-context workloads. Released under the Apache 2.0 license, it builds on earlier Qwen multimodal systems and provides developers with an open-weight model capable of handling demanding multimodal reasoning and analysis tasks.