June 2, 2024
This is extremely cool and very elegantly done.
It's also a very nice pointer to the near future of AI. Running small LLMs locally on-device is going to enable a *lot* of new capabilities. And hybrid approaches that use both local and cloud inference are going to become a standard application architecture.
gm gm, excited to share what we've been working for more than a year at Puma ✨
tl;dr: Native integration of @OpenAI, @AnthropicAI and @GoogleDevs Gemini and Local LLMs on your mobile phone 🤖📱
Quick thread:
