Well that was an interesting afternoon. Installed Tinyllama on my Phosh (PostmarketOS) OnePlus 6. Of course, it ran a bit slow (with only 5gb RAm available) and
A user successfully installed the TinyLlama AI model on a OnePlus 6 smartphone running PostmarketOS with the Phosh interface. While the model's performance was slow and its output quality was not exceptional due to the limited 5GB of RAM, the experiment demonstrated the possibility of running AI locally on mobile Linux devices. The user expressed a preference for local AI execution over cloud-based solutions. AI
IMPACT Demonstrates feasibility of running smaller AI models on resource-constrained mobile devices, catering to privacy-focused local AI execution.