Llama 3.2-Vision

The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative…

Lifecycle

Active

Release date

Sep 25, 2024

Availability

Available in

Availability remains unknown until verified coding-agent sources are connected.

Claude CodeUnknown ClineUnknown CodexUnknown CursorUnknown GitHub CopilotUnknown ReplitUnknown WindsurfUnknown

Specifications

Model details

Context window: 128,000 tokens
Max output: Coming soon
Input types: Image, Text
Output types: Text
Reasoning support: Coming soon
Vision support: Supported
API availability: Coming soon
Knowledge cutoff: December 2023

Changelog

Recent changes

2024-09-25T00:00:00.000Z

Model released

Official documentation records the release of Llama 3.2-Vision.

Sources / Verification

Official sources used for this model.

Meta Llama model registry ↗

VerificationOfficial source