Qualcomm launches two new smartphone chips with emphasis on AI

AI News & Artificial Intelligence | TechCrunch · 1d ago
Model Releases LLMs

How-To How to actually use this

What changed: Qualcomm launched a new top smartphone chip that can run a 30B mixture-of-expert model locally.

How to use it:

  1. Download a compatible 30B MoE model to your device.
  2. Ensure the model is in a supported format for on-device execution.
  3. Run inference directly on the device without an internet connection.
  4. Monitor performance and battery usage during local model execution.

Good for: developers testing on-device AI models

Qualcomm said that its new top chip can run 30B mixture-of-expert model locally.

Read original article on AI News & Artificial Intelligence | TechCrunch →