[GH-ISSUE #8750] Support for Llama 3.2 3B Model Deployment on EC2 (CPU-Only) #83362

Closed
opened 2026-05-09 17:56:41 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @ganesh-gupta-clapself on GitHub (Feb 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8750

I would like to deploy the Llama 3.2 3B model on an EC2 instance using Ollama with CPU-only inference. Could you recommend the best EC2 instance type for this setup?

Key considerations:

No GPU, only CPU usage.
Optimized for running Llama 3B efficiently.
Reasonable inference speed for real-world applications.
Additionally, if there are any specific configurations, optimizations, or dependencies required to improve performance, please let me know.

Thanks in advance!

Originally created by @ganesh-gupta-clapself on GitHub (Feb 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8750 I would like to deploy the Llama 3.2 3B model on an EC2 instance using Ollama with CPU-only inference. Could you recommend the best EC2 instance type for this setup? Key considerations: No GPU, only CPU usage. Optimized for running Llama 3B efficiently. Reasonable inference speed for real-world applications. Additionally, if there are any specific configurations, optimizations, or dependencies required to improve performance, please let me know. Thanks in advance!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#83362