Roboflow

MetaMetaReleased Sep 2024Proprietary

Llama 3.2 Vision 90b

Llama 3.2 Vision 90b is deprecated and can't be run here.

We don't benchmark Llama 3.2 Vision 90b. It is a proprietary model from Meta, so commercial use follows Meta's terms.

This model is deprecated

Llama 3.2 Vision 90b and can no longer be run here. Its details remain available for reference.

Llama 3.2 Vision 90b Overview

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.

Llama 3.2 Vision 90b License

Proprietary

Llama 3.2 Vision 90b is proprietary: the weights are not distributed, and the Llama 3.2 Vision 90b license is the vendor's commercial terms of service that you accept when you call the API.

Commercial use
Permitted under the vendor terms, typically metered per token or per request, with the vendor usage policy applying to your inputs and outputs.
Modification
Not available. Llama 3.2 Vision 90b weights are closed, so you can configure prompts and use vendor-hosted fine-tuning where it is offered, but you cannot modify the model itself.
Redistribution
Not permitted. You cannot self-host or resell the model; you build on the hosted API instead.

Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.

Do I need a commercial license for Llama 3.2 Vision 90b?

Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy an open model instead of Llama 3.2 Vision 90b, Roboflow's licensing page lists the models whose commercial license is included when you deploy on Roboflow.

Do not hesitate to reach out with questions for your commercial project. Our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.

Talk to sales

License information is provided as a guide and is not legal advice.

Llama 3.2 Vision 90b Details

Details

Categoryopen
ModalityMultimodal
Context Window128K
Parameters90B
LicenseProprietary
Release DateSep 2024

Vision Tasks

CaptioningChart Question AnsweringClassificationDocument Question AnsweringImage TaggingMulti-Label ClassificationOCRVision LanguageVisual Question Answering

Alternatives to Llama 3.2 Vision 90b

Other models worth comparing for similar use cases.

Muse Ember is a proprietary multimodal reasoning model from Meta, released on November 9, 2026.
Muse Wonder is a proprietary multimodal reasoning model from Meta, released on October 12, 2026 as the first step past the Muse Spark line on Meta's scaling ladder.
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.
Gemini 3.1 Pro is a proprietary multimodal model from Google’s Gemini 3 series, released in early 2026 and designed for advanced reasoning across large multimodal datasets.
Claude Opus 4.7 is a proprietary multimodal language model developed by Anthropic, released on April 16, 2026.
GPT-6.1 Sol is a reasoning model in OpenAI's GPT-6 series that accepts text and image input and returns text.