LLM: Llama 3.2

Developer

Meta

Genealogy

LLaMA → Llama 2 → Llama 3 → Llama 3.1 → Llama 3.2

Initial Release

2024-09-25

Overview

Llama 3.2 introduced multimodal vision models (11B and 90B) alongside lightweight text-only models (1B and 3B) designed for on-device and edge deployment.

Description

Llama 3.2 expanded Meta's open-source model family in two directions. The vision models (11B and 90B) are the first Llama models to support image understanding, enabling tasks such as chart analysis, document parsing, and visual question answering. The lightweight text models (1B and 3B) are optimised for on-device inference, with quantised versions available for mobile and edge hardware. All models benefit from the architectural improvements introduced in Llama 3.1.

Open Source

Yes

Instruct Tuned

Yes

Model Sizes

1B, 3B, 11B, 90B

Finetuning

Yes

License

Custom (Commercial OK)

Pricing

-

Link

Visit

Further Reading

• https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/
• https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct

Unsure? Contact us with a brief description of your use case if you'd like for us to make a snap assessment. Depending on your requirements, a smaller, custom language model may even be the best option.