Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Llama 3.2 Vision · Ollama Blog

Nov 06, 2024 - ollama.com
The article announces the availability of Llama 3.2 Vision to run in Ollama, in both 11B and 90B sizes. To get started, users need to download Ollama 0.4 and run specific commands. The 11B model requires at least 8GB of VRAM, while the 90B model needs a minimum of 64GB of VRAM. Users can add an image to the prompt by dragging and dropping it into the terminal or adding a path to the image on Linux.

The article also provides examples of usage, such as handwriting, optical character recognition (OCR), charts and tables, and image Q&A. It further explains how to use Llama 3.2 Vision with the Ollama Python library, the Ollama JavaScript library, and cURL. The process involves importing Ollama, setting up a chat model, and defining the user role and content.

Key takeaways:

  • Llama 3.2 Vision is now available to run in Ollama, in both 11B and 90B sizes.
  • To run the program, users need to download Ollama 0.4 and use specific commands for the 11B or 90B model.
  • Llama 3.2 Vision can be used with the Ollama Python library, the Ollama JavaScript library, or cURL.
  • The 11B model requires at least 8GB of VRAM, and the 90B model requires at least 64 GB of VRAM.
View Full Article

Comments (0)

Be the first to comment!