11 min read
Running Gemma 4 Locally on iOS and Android: The Google AI Edge Gallery Guide
Step-by-step guide to run Gemma 4 locally on iPhone or Android via Google AI Edge Gallery. Learn how Multi-Token Prediction unlocks fast on-device agents.
Article
Articles and technical notes on distributed systems, TypeScript architecture, web performance, and developer tools by Nishchay Kaushik.
5 min read
How to Install and Run Ollama in Termux on Android (2026 Guide)
Step-by-step guide to run Ollama in Termux on Android. Run lightweight Qwen 2.5, Gemma & Llama models with one-line install, WebUI, and no root.
7 min read
Top 4 ways to Run LLM locally on Android and iOS
Compare best local LLM apps for Android & iOS in 2026 (PocketPal, Edge Gallery, Termux, AnythingLLM). Zero data leaks, offline mode & uncensored models.
11 min read
Replace Google Photos: Self‑Host Immich in 2026
A step-by-step tutorial on setting up Immich with Docker, Cloudflare, and Tailscale. Secure your photos without the recurring cloud costs.
8 min read
Getting Started with Self-Hosting in 2026
Start your self-hosting journey in 2026. Learn how to choose the right hardware, configure Debian 13, and deploy Docker containers for your homelab.
7 min read
AdGuard Home: Stop Ads & Trackers for Your Entire Family (2026)
The 2026 AdGuard Home guide: copy-paste recommended blocklists, optimize upstream DNS settings, block malware, and set up parental controls network-wide.
5 min read
Running 24/7 Local AI on an Old Android without Overheating
Learn how to run local AI models 24/7 on an old Android phone without overheating using Advanced Charging Control (ACC) and llama-server.
4 min read
How to Run LLM Models on Old Android Devices Locally
Turn an old 2GB–4GB Android phone into an offline AI server using llama.cpp in Termux. Fix memory errors, optimize CPU threads, and prevent overheating.
2 min read
Hello World!
Insights from Nishchay on AI, self-hosting, performance testing, frontend tech, and cloud services