https://deardhruv.com/tags/llama.cpp/Recent content in Llama.cpp on Dhruv Patel - Lead Android EngineerHugoendhruv.time@gmail.com (Dhruv Patel)dhruv.time@gmail.com (Dhruv Patel)<a href="https://creativecommons.org/licenses/by-nc/4.0/" target="_blank" rel="noopener">CC BY-NC 4.0</a>Mon, 05 Oct 2026 16:26:02 +0530https://deardhruv.com/posts/ai_playground_series/01-i-wanted-the-model-to-stay-on-the-phone/Mon, 05 Oct 2026 10:00:00 +0530dhruv.time@gmail.com (Dhruv Patel)https://deardhruv.com/posts/ai_playground_series/01-i-wanted-the-model-to-stay-on-the-phone/<h1 id="beyond-the-model-building-a-private-ai-playground-for-android--ios">Beyond the Model: Building a Private AI Playground for Android &amp; iOS</h1> <h2 id="part-1---i-wanted-the-model-to-stay-on-the-phone">Part 1 - I Wanted the Model to Stay on the Phone</h2> <h3 id="the-engineering-journey-of-integrating-established-on-device-ai-runtimes-into-one-multimodal-mobile-product---and-everything-it-takes-to-make-the-pieces-behave-like-a-coherent-system">The engineering journey of integrating established on-device AI runtimes into one multimodal mobile product - and everything it takes to make the pieces behave like a coherent system</h3> <p>There was one constraint behind AI Playground that shaped almost every architectural decision that came after it:</p> <blockquote> <p><strong>I did not want the core AI workflow to depend on a server.</strong></p>